Documentation ¶
Overview ¶
Package speech provides access to the Cloud Speech-to-Text API.
This package is DEPRECATED. Use package cloud.google.com/go/speech/apiv1 instead.
For product documentation, see: https://cloud.google.com/speech-to-text/docs/quickstart-protocol
Creating a client ¶
Usage example:
import "google.golang.org/api/speech/v1p1beta1" ... ctx := context.Background() speechService, err := speech.NewService(ctx)
In this example, Google Application Default Credentials are used for authentication.
For information on how to create and obtain Application Default Credentials, see https://developers.google.com/identity/protocols/application-default-credentials.
Other authentication options ¶
To use an API key for authentication (note: some APIs do not support API keys), use option.WithAPIKey:
speechService, err := speech.NewService(ctx, option.WithAPIKey("AIza..."))
To use an OAuth token (e.g., a user token obtained via a three-legged OAuth flow), use option.WithTokenSource:
config := &oauth2.Config{...} // ... token, err := config.Exchange(ctx, ...) speechService, err := speech.NewService(ctx, option.WithTokenSource(config.TokenSource(ctx, token)))
See https://godoc.org/google.golang.org/api/option/ for details on options.
Index ¶
- Constants
- type ClassItem
- type CustomClass
- type ListOperationsResponse
- type LongRunningRecognizeMetadata
- type LongRunningRecognizeRequest
- type LongRunningRecognizeResponse
- type Operation
- type OperationsGetCall
- func (c *OperationsGetCall) Context(ctx context.Context) *OperationsGetCall
- func (c *OperationsGetCall) Do(opts ...googleapi.CallOption) (*Operation, error)
- func (c *OperationsGetCall) Fields(s ...googleapi.Field) *OperationsGetCall
- func (c *OperationsGetCall) Header() http.Header
- func (c *OperationsGetCall) IfNoneMatch(entityTag string) *OperationsGetCall
- type OperationsListCall
- func (c *OperationsListCall) Context(ctx context.Context) *OperationsListCall
- func (c *OperationsListCall) Do(opts ...googleapi.CallOption) (*ListOperationsResponse, error)
- func (c *OperationsListCall) Fields(s ...googleapi.Field) *OperationsListCall
- func (c *OperationsListCall) Filter(filter string) *OperationsListCall
- func (c *OperationsListCall) Header() http.Header
- func (c *OperationsListCall) IfNoneMatch(entityTag string) *OperationsListCall
- func (c *OperationsListCall) Name(name string) *OperationsListCall
- func (c *OperationsListCall) PageSize(pageSize int64) *OperationsListCall
- func (c *OperationsListCall) PageToken(pageToken string) *OperationsListCall
- func (c *OperationsListCall) Pages(ctx context.Context, f func(*ListOperationsResponse) error) error
- type OperationsService
- type Phrase
- type PhraseSet
- type ProjectsLocationsOperationsGetCall
- func (c *ProjectsLocationsOperationsGetCall) Context(ctx context.Context) *ProjectsLocationsOperationsGetCall
- func (c *ProjectsLocationsOperationsGetCall) Do(opts ...googleapi.CallOption) (*Operation, error)
- func (c *ProjectsLocationsOperationsGetCall) Fields(s ...googleapi.Field) *ProjectsLocationsOperationsGetCall
- func (c *ProjectsLocationsOperationsGetCall) Header() http.Header
- func (c *ProjectsLocationsOperationsGetCall) IfNoneMatch(entityTag string) *ProjectsLocationsOperationsGetCall
- type ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) Context(ctx context.Context) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) Do(opts ...googleapi.CallOption) (*ListOperationsResponse, error)
- func (c *ProjectsLocationsOperationsListCall) Fields(s ...googleapi.Field) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) Filter(filter string) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) Header() http.Header
- func (c *ProjectsLocationsOperationsListCall) IfNoneMatch(entityTag string) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) PageSize(pageSize int64) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) PageToken(pageToken string) *ProjectsLocationsOperationsListCall
- func (c *ProjectsLocationsOperationsListCall) Pages(ctx context.Context, f func(*ListOperationsResponse) error) error
- type ProjectsLocationsOperationsService
- type ProjectsLocationsService
- type ProjectsService
- type RecognitionAudio
- type RecognitionConfig
- type RecognitionMetadata
- type RecognizeRequest
- type RecognizeResponse
- type Service
- type SpeakerDiarizationConfig
- type SpeechAdaptation
- type SpeechContext
- type SpeechLongrunningrecognizeCall
- func (c *SpeechLongrunningrecognizeCall) Context(ctx context.Context) *SpeechLongrunningrecognizeCall
- func (c *SpeechLongrunningrecognizeCall) Do(opts ...googleapi.CallOption) (*Operation, error)
- func (c *SpeechLongrunningrecognizeCall) Fields(s ...googleapi.Field) *SpeechLongrunningrecognizeCall
- func (c *SpeechLongrunningrecognizeCall) Header() http.Header
- type SpeechRecognitionAlternative
- type SpeechRecognitionResult
- type SpeechRecognizeCall
- func (c *SpeechRecognizeCall) Context(ctx context.Context) *SpeechRecognizeCall
- func (c *SpeechRecognizeCall) Do(opts ...googleapi.CallOption) (*RecognizeResponse, error)
- func (c *SpeechRecognizeCall) Fields(s ...googleapi.Field) *SpeechRecognizeCall
- func (c *SpeechRecognizeCall) Header() http.Header
- type SpeechService
- type Status
- type WordInfo
Constants ¶
const (
// View and manage your data across Google Cloud Platform services
CloudPlatformScope = "https://www.googleapis.com/auth/cloud-platform"
)
OAuth2 scopes used by this API.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type ClassItem ¶ added in v0.23.0
type ClassItem struct { // Value: The class item's value. Value string `json:"value,omitempty"` // ForceSendFields is a list of field names (e.g. "Value") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Value") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
ClassItem: An item of the class.
func (*ClassItem) MarshalJSON ¶ added in v0.23.0
type CustomClass ¶ added in v0.23.0
type CustomClass struct { // CustomClassId: If this custom class is a resource, the // custom_class_id is the resource id // of the CustomClass. CustomClassId string `json:"customClassId,omitempty"` // Items: A collection of class items. Items []*ClassItem `json:"items,omitempty"` // Name: The resource name of the custom class. Name string `json:"name,omitempty"` // ForceSendFields is a list of field names (e.g. "CustomClassId") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "CustomClassId") to include // in API requests with the JSON null value. By default, fields with // empty values are omitted from API requests. However, any field with // an empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
CustomClass: A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases.
func (*CustomClass) MarshalJSON ¶ added in v0.23.0
func (s *CustomClass) MarshalJSON() ([]byte, error)
type ListOperationsResponse ¶
type ListOperationsResponse struct { // NextPageToken: The standard List next-page token. NextPageToken string `json:"nextPageToken,omitempty"` // Operations: A list of operations that matches the specified filter in // the request. Operations []*Operation `json:"operations,omitempty"` // ServerResponse contains the HTTP response code and headers from the // server. googleapi.ServerResponse `json:"-"` // ForceSendFields is a list of field names (e.g. "NextPageToken") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "NextPageToken") to include // in API requests with the JSON null value. By default, fields with // empty values are omitted from API requests. However, any field with // an empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
ListOperationsResponse: The response message for Operations.ListOperations.
func (*ListOperationsResponse) MarshalJSON ¶
func (s *ListOperationsResponse) MarshalJSON() ([]byte, error)
type LongRunningRecognizeMetadata ¶
type LongRunningRecognizeMetadata struct { // LastUpdateTime: Time of the most recent processing update. LastUpdateTime string `json:"lastUpdateTime,omitempty"` // ProgressPercent: Approximate percentage of audio processed thus far. // Guaranteed to be 100 // when the audio is fully processed and the results are available. ProgressPercent int64 `json:"progressPercent,omitempty"` // StartTime: Time when the request was received. StartTime string `json:"startTime,omitempty"` // Uri: Output only. The URI of the audio file being transcribed. Empty // if the audio was sent // as byte content. Uri string `json:"uri,omitempty"` // ForceSendFields is a list of field names (e.g. "LastUpdateTime") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "LastUpdateTime") to // include in API requests with the JSON null value. By default, fields // with empty values are omitted from API requests. However, any field // with an empty value appearing in NullFields will be sent to the // server as null. It is an error if a field in this list has a // non-empty value. This may be used to include null fields in Patch // requests. NullFields []string `json:"-"` }
LongRunningRecognizeMetadata: Describes the progress of a long-running `LongRunningRecognize` call. It is included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
func (*LongRunningRecognizeMetadata) MarshalJSON ¶
func (s *LongRunningRecognizeMetadata) MarshalJSON() ([]byte, error)
type LongRunningRecognizeRequest ¶
type LongRunningRecognizeRequest struct { // Audio: Required. The audio data to be recognized. Audio *RecognitionAudio `json:"audio,omitempty"` // Config: Required. Provides information to the recognizer that // specifies how to // process the request. Config *RecognitionConfig `json:"config,omitempty"` // ForceSendFields is a list of field names (e.g. "Audio") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Audio") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
LongRunningRecognizeRequest: The top-level message sent by the client for the `LongRunningRecognize` method.
func (*LongRunningRecognizeRequest) MarshalJSON ¶
func (s *LongRunningRecognizeRequest) MarshalJSON() ([]byte, error)
type LongRunningRecognizeResponse ¶
type LongRunningRecognizeResponse struct { // Results: Sequential list of transcription results corresponding // to // sequential portions of audio. Results []*SpeechRecognitionResult `json:"results,omitempty"` // ForceSendFields is a list of field names (e.g. "Results") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Results") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
LongRunningRecognizeResponse: The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
func (*LongRunningRecognizeResponse) MarshalJSON ¶
func (s *LongRunningRecognizeResponse) MarshalJSON() ([]byte, error)
type Operation ¶
type Operation struct { // Done: If the value is `false`, it means the operation is still in // progress. // If `true`, the operation is completed, and either `error` or // `response` is // available. Done bool `json:"done,omitempty"` // Error: The error result of the operation in case of failure or // cancellation. Error *Status `json:"error,omitempty"` // Metadata: Service-specific metadata associated with the operation. // It typically // contains progress information and common metadata such as create // time. // Some services might not provide such metadata. Any method that // returns a // long-running operation should document the metadata type, if any. Metadata googleapi.RawMessage `json:"metadata,omitempty"` // Name: The server-assigned name, which is only unique within the same // service that // originally returns it. If you use the default HTTP mapping, // the // `name` should be a resource name ending with // `operations/{unique_id}`. Name string `json:"name,omitempty"` // Response: The normal response of the operation in case of success. // If the original // method returns no data on success, such as `Delete`, the response // is // `google.protobuf.Empty`. If the original method is // standard // `Get`/`Create`/`Update`, the response should be the resource. For // other // methods, the response should have the type `XxxResponse`, where // `Xxx` // is the original method name. For example, if the original method // name // is `TakeSnapshot()`, the inferred response type // is // `TakeSnapshotResponse`. Response googleapi.RawMessage `json:"response,omitempty"` // ServerResponse contains the HTTP response code and headers from the // server. googleapi.ServerResponse `json:"-"` // ForceSendFields is a list of field names (e.g. "Done") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Done") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
Operation: This resource represents a long-running operation that is the result of a network API call.
func (*Operation) MarshalJSON ¶
type OperationsGetCall ¶
type OperationsGetCall struct {
// contains filtered or unexported fields
}
func (*OperationsGetCall) Context ¶
func (c *OperationsGetCall) Context(ctx context.Context) *OperationsGetCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*OperationsGetCall) Do ¶
func (c *OperationsGetCall) Do(opts ...googleapi.CallOption) (*Operation, error)
Do executes the "speech.operations.get" call. Exactly one of *Operation or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *Operation.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*OperationsGetCall) Fields ¶
func (c *OperationsGetCall) Fields(s ...googleapi.Field) *OperationsGetCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*OperationsGetCall) Header ¶
func (c *OperationsGetCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
func (*OperationsGetCall) IfNoneMatch ¶
func (c *OperationsGetCall) IfNoneMatch(entityTag string) *OperationsGetCall
IfNoneMatch sets the optional parameter which makes the operation fail if the object's ETag matches the given value. This is useful for getting updates only after the object has changed since the last request. Use googleapi.IsNotModified to check whether the response error from Do is the result of In-None-Match.
type OperationsListCall ¶
type OperationsListCall struct {
// contains filtered or unexported fields
}
func (*OperationsListCall) Context ¶
func (c *OperationsListCall) Context(ctx context.Context) *OperationsListCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*OperationsListCall) Do ¶
func (c *OperationsListCall) Do(opts ...googleapi.CallOption) (*ListOperationsResponse, error)
Do executes the "speech.operations.list" call. Exactly one of *ListOperationsResponse or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *ListOperationsResponse.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*OperationsListCall) Fields ¶
func (c *OperationsListCall) Fields(s ...googleapi.Field) *OperationsListCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*OperationsListCall) Filter ¶
func (c *OperationsListCall) Filter(filter string) *OperationsListCall
Filter sets the optional parameter "filter": The standard list filter.
func (*OperationsListCall) Header ¶
func (c *OperationsListCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
func (*OperationsListCall) IfNoneMatch ¶
func (c *OperationsListCall) IfNoneMatch(entityTag string) *OperationsListCall
IfNoneMatch sets the optional parameter which makes the operation fail if the object's ETag matches the given value. This is useful for getting updates only after the object has changed since the last request. Use googleapi.IsNotModified to check whether the response error from Do is the result of In-None-Match.
func (*OperationsListCall) Name ¶
func (c *OperationsListCall) Name(name string) *OperationsListCall
Name sets the optional parameter "name": The name of the operation's parent resource.
func (*OperationsListCall) PageSize ¶
func (c *OperationsListCall) PageSize(pageSize int64) *OperationsListCall
PageSize sets the optional parameter "pageSize": The standard list page size.
func (*OperationsListCall) PageToken ¶
func (c *OperationsListCall) PageToken(pageToken string) *OperationsListCall
PageToken sets the optional parameter "pageToken": The standard list page token.
func (*OperationsListCall) Pages ¶
func (c *OperationsListCall) Pages(ctx context.Context, f func(*ListOperationsResponse) error) error
Pages invokes f for each page of results. A non-nil error returned from f will halt the iteration. The provided context supersedes any context provided to the Context method.
type OperationsService ¶
type OperationsService struct {
// contains filtered or unexported fields
}
func NewOperationsService ¶
func NewOperationsService(s *Service) *OperationsService
func (*OperationsService) Get ¶
func (r *OperationsService) Get(name string) *OperationsGetCall
Get: Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
func (*OperationsService) List ¶
func (r *OperationsService) List() *OperationsListCall
List: Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.
NOTE: the `name` binding allows API services to override the binding to use different resource name schemes, such as `users/*/operations`. To override the binding, API services can add a binding such as "/v1/{name=users/*}/operations" to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.
type Phrase ¶ added in v0.23.0
type Phrase struct { // Boost: Hint Boost. Overrides the boost set at the phrase set // level. // Positive value will increase the probability that a specific phrase // will // be recognized over other similar sounding phrases. The higher the // boost, // the higher the chance of false positive recognition as well. // Negative // boost values would correspond to anti-biasing. Anti-biasing is // not // enabled, so negative boost will simply be ignored. Though `boost` // can // accept a wide range of positive values, most use cases are best // served // with values between 0 and 20. We recommend using a binary search // approach // to finding the optimal value for your use case. Speech // recognition // will skip PhraseSets with a boost value of 0. Boost float64 `json:"boost,omitempty"` // Value: The phrase itself. Value string `json:"value,omitempty"` // ForceSendFields is a list of field names (e.g. "Boost") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Boost") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
Phrase: A phrases containing words and phrase "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech-to-text/quotas#content).
List
items can also include pre-built or custom classes containing
groups of words that represent common concepts that occur in natural language. For example, rather than providing a phrase hint for every month of the year (e.g. "i was born in january", "i was born in febuary", ...), use the pre-built $MONTH class improves the likelihood of correctly transcribing audio that includes months (e.g. "i was born in $month"). To refer to pre-built classes, use the class' symbol prepended with $ e.g. $MONTH. To refer to custom classes that were defined inline in the request, set the class's `custom_class_id` to a string unique to all class resources and inline classes. Then use the class' id wrapped in ${...} e.g. "${my-months}". To refer to custom classes resources, use the class' id wrapped in ${} (e.g. ${my-months}).
func (*Phrase) MarshalJSON ¶ added in v0.23.0
func (*Phrase) UnmarshalJSON ¶ added in v0.23.0
type PhraseSet ¶ added in v0.23.0
type PhraseSet struct { // Boost: Hint Boost. Positive value will increase the probability that // a specific // phrase will be recognized over other similar sounding phrases. The // higher // the boost, the higher the chance of false positive recognition as // well. // Negative boost values would correspond to anti-biasing. Anti-biasing // is not // enabled, so negative boost will simply be ignored. Though `boost` // can // accept a wide range of positive values, most use cases are best // served with // values between 0 (exclusive) and 20. We recommend using a binary // search // approach to finding the optimal value for your use case. Speech // recognition // will skip PhraseSets with a boost value of 0. Boost float64 `json:"boost,omitempty"` // Name: The resource name of the phrase set. Name string `json:"name,omitempty"` // Phrases: A list of word and phrases. Phrases []*Phrase `json:"phrases,omitempty"` // ForceSendFields is a list of field names (e.g. "Boost") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Boost") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
PhraseSet: Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
func (*PhraseSet) MarshalJSON ¶ added in v0.23.0
func (*PhraseSet) UnmarshalJSON ¶ added in v0.23.0
type ProjectsLocationsOperationsGetCall ¶ added in v0.2.0
type ProjectsLocationsOperationsGetCall struct {
// contains filtered or unexported fields
}
func (*ProjectsLocationsOperationsGetCall) Context ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsGetCall) Context(ctx context.Context) *ProjectsLocationsOperationsGetCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*ProjectsLocationsOperationsGetCall) Do ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsGetCall) Do(opts ...googleapi.CallOption) (*Operation, error)
Do executes the "speech.projects.locations.operations.get" call. Exactly one of *Operation or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *Operation.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*ProjectsLocationsOperationsGetCall) Fields ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsGetCall) Fields(s ...googleapi.Field) *ProjectsLocationsOperationsGetCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*ProjectsLocationsOperationsGetCall) Header ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsGetCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
func (*ProjectsLocationsOperationsGetCall) IfNoneMatch ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsGetCall) IfNoneMatch(entityTag string) *ProjectsLocationsOperationsGetCall
IfNoneMatch sets the optional parameter which makes the operation fail if the object's ETag matches the given value. This is useful for getting updates only after the object has changed since the last request. Use googleapi.IsNotModified to check whether the response error from Do is the result of In-None-Match.
type ProjectsLocationsOperationsListCall ¶ added in v0.2.0
type ProjectsLocationsOperationsListCall struct {
// contains filtered or unexported fields
}
func (*ProjectsLocationsOperationsListCall) Context ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Context(ctx context.Context) *ProjectsLocationsOperationsListCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*ProjectsLocationsOperationsListCall) Do ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Do(opts ...googleapi.CallOption) (*ListOperationsResponse, error)
Do executes the "speech.projects.locations.operations.list" call. Exactly one of *ListOperationsResponse or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *ListOperationsResponse.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*ProjectsLocationsOperationsListCall) Fields ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Fields(s ...googleapi.Field) *ProjectsLocationsOperationsListCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*ProjectsLocationsOperationsListCall) Filter ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Filter(filter string) *ProjectsLocationsOperationsListCall
Filter sets the optional parameter "filter": The standard list filter.
func (*ProjectsLocationsOperationsListCall) Header ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
func (*ProjectsLocationsOperationsListCall) IfNoneMatch ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) IfNoneMatch(entityTag string) *ProjectsLocationsOperationsListCall
IfNoneMatch sets the optional parameter which makes the operation fail if the object's ETag matches the given value. This is useful for getting updates only after the object has changed since the last request. Use googleapi.IsNotModified to check whether the response error from Do is the result of In-None-Match.
func (*ProjectsLocationsOperationsListCall) PageSize ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) PageSize(pageSize int64) *ProjectsLocationsOperationsListCall
PageSize sets the optional parameter "pageSize": The standard list page size.
func (*ProjectsLocationsOperationsListCall) PageToken ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) PageToken(pageToken string) *ProjectsLocationsOperationsListCall
PageToken sets the optional parameter "pageToken": The standard list page token.
func (*ProjectsLocationsOperationsListCall) Pages ¶ added in v0.2.0
func (c *ProjectsLocationsOperationsListCall) Pages(ctx context.Context, f func(*ListOperationsResponse) error) error
Pages invokes f for each page of results. A non-nil error returned from f will halt the iteration. The provided context supersedes any context provided to the Context method.
type ProjectsLocationsOperationsService ¶ added in v0.2.0
type ProjectsLocationsOperationsService struct {
// contains filtered or unexported fields
}
func NewProjectsLocationsOperationsService ¶ added in v0.2.0
func NewProjectsLocationsOperationsService(s *Service) *ProjectsLocationsOperationsService
func (*ProjectsLocationsOperationsService) Get ¶ added in v0.2.0
func (r *ProjectsLocationsOperationsService) Get(name string) *ProjectsLocationsOperationsGetCall
Get: Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
func (*ProjectsLocationsOperationsService) List ¶ added in v0.2.0
func (r *ProjectsLocationsOperationsService) List(name string) *ProjectsLocationsOperationsListCall
List: Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.
NOTE: the `name` binding allows API services to override the binding to use different resource name schemes, such as `users/*/operations`. To override the binding, API services can add a binding such as "/v1/{name=users/*}/operations" to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.
type ProjectsLocationsService ¶ added in v0.2.0
type ProjectsLocationsService struct { Operations *ProjectsLocationsOperationsService // contains filtered or unexported fields }
func NewProjectsLocationsService ¶ added in v0.2.0
func NewProjectsLocationsService(s *Service) *ProjectsLocationsService
type ProjectsService ¶ added in v0.2.0
type ProjectsService struct { Locations *ProjectsLocationsService // contains filtered or unexported fields }
func NewProjectsService ¶ added in v0.2.0
func NewProjectsService(s *Service) *ProjectsService
type RecognitionAudio ¶
type RecognitionAudio struct { // Content: The audio data bytes encoded as specified // in // `RecognitionConfig`. Note: as with all bytes fields, proto buffers // use a // pure binary representation, whereas JSON representations use base64. Content string `json:"content,omitempty"` // Uri: URI that points to a file that contains audio data bytes as // specified in // `RecognitionConfig`. The file must not be compressed (for example, // gzip). // Currently, only Google Cloud Storage URIs are // supported, which must be specified in the following // format: // `gs://bucket_name/object_name` (other URI formats // return // google.rpc.Code.INVALID_ARGUMENT). For more information, see // [Request URIs](https://cloud.google.com/storage/docs/reference-uris). Uri string `json:"uri,omitempty"` // ForceSendFields is a list of field names (e.g. "Content") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Content") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
RecognitionAudio: Contains audio data in the encoding specified in the `RecognitionConfig`. Either `content` or `uri` must be supplied. Supplying both or neither returns google.rpc.Code.INVALID_ARGUMENT. See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
func (*RecognitionAudio) MarshalJSON ¶
func (s *RecognitionAudio) MarshalJSON() ([]byte, error)
type RecognitionConfig ¶
type RecognitionConfig struct { // Adaptation: Speech adaptation configuration improves the accuracy of // speech // recognition. When speech adaptation is set it supersedes // the // `speech_contexts` field. For more information, see the // [speech // adaptation](https://cloud.google.com/speech-to-text/docs/conte // xt-strength) // documentation. Adaptation *SpeechAdaptation `json:"adaptation,omitempty"` // AlternativeLanguageCodes: A list of up to 3 // additional // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language // tags, // listing possible alternative languages of the supplied audio. // See // [Language // Support](https://cloud.google.com/speech-to-text/docs/langua // ges) for a list // of the currently supported language codes. If alternative languages // are // listed, recognition result will contain recognition in the most // likely // language detected including the main language_code. The recognition // result // will include the language tag of the language detected in the audio. // Note: // This feature is only supported for Voice Command and Voice Search use // cases // and performance may vary for other use cases (e.g., phone // call // transcription). AlternativeLanguageCodes []string `json:"alternativeLanguageCodes,omitempty"` // AudioChannelCount: The number of channels in the input audio // data. // ONLY set this for MULTI-CHANNEL recognition. // Valid values for LINEAR16 and FLAC are `1`-`8`. // Valid values for OGG_OPUS are '1'-'254'. // Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only // `1`. // If `0` or omitted, defaults to one channel (mono). // Note: We only recognize the first channel by default. // To perform independent recognition on each channel // set // `enable_separate_recognition_per_channel` to 'true'. AudioChannelCount int64 `json:"audioChannelCount,omitempty"` // DiarizationConfig: Config to enable speaker diarization and set // additional // parameters to make diarization better suited for your // application. // Note: When this is enabled, we send all the words from the beginning // of the // audio for the top alternative in every consecutive STREAMING // responses. // This is done in order to improve our speaker tags as our models learn // to // identify the speakers in the conversation over time. // For non-streaming requests, the diarization results will be provided // only // in the top alternative of the FINAL SpeechRecognitionResult. DiarizationConfig *SpeakerDiarizationConfig `json:"diarizationConfig,omitempty"` // DiarizationSpeakerCount: If set, specifies the estimated number of // speakers in the conversation. // Defaults to '2'. Ignored unless enable_speaker_diarization is set to // true. // Note: Use diarization_config instead. DiarizationSpeakerCount int64 `json:"diarizationSpeakerCount,omitempty"` // EnableAutomaticPunctuation: If 'true', adds punctuation to // recognition result hypotheses. // This feature is only available in select languages. Setting this // for // requests in other languages has no effect at all. // The default 'false' value does not add punctuation to result // hypotheses. EnableAutomaticPunctuation bool `json:"enableAutomaticPunctuation,omitempty"` // EnableSeparateRecognitionPerChannel: This needs to be set to `true` // explicitly and `audio_channel_count` > 1 // to get each channel recognized separately. The recognition result // will // contain a `channel_tag` field to state which channel that result // belongs // to. If this is not true, we will only recognize the first channel. // The // request is billed cumulatively for all channels // recognized: // `audio_channel_count` multiplied by the length of the audio. EnableSeparateRecognitionPerChannel bool `json:"enableSeparateRecognitionPerChannel,omitempty"` // EnableSpeakerDiarization: If 'true', enables speaker detection for // each recognized word in // the top alternative of the recognition result using a speaker_tag // provided // in the WordInfo. // Note: Use diarization_config instead. EnableSpeakerDiarization bool `json:"enableSpeakerDiarization,omitempty"` // EnableWordConfidence: If `true`, the top result includes a list of // words and the // confidence for those words. If `false`, no word-level // confidence // information is returned. The default is `false`. EnableWordConfidence bool `json:"enableWordConfidence,omitempty"` // EnableWordTimeOffsets: If `true`, the top result includes a list of // words and // the start and end time offsets (timestamps) for those words. // If // `false`, no word-level time offset information is returned. The // default is // `false`. EnableWordTimeOffsets bool `json:"enableWordTimeOffsets,omitempty"` // Encoding: Encoding of audio data sent in all `RecognitionAudio` // messages. // This field is optional for `FLAC` and `WAV` audio files and // required // for all other audio formats. For details, see AudioEncoding. // // Possible values: // "ENCODING_UNSPECIFIED" - Not specified. // "LINEAR16" - Uncompressed 16-bit signed little-endian samples // (Linear PCM). // "FLAC" - `FLAC` (Free Lossless Audio // Codec) is the recommended encoding because it is // lossless--therefore recognition is not compromised--and // requires only about half the bandwidth of `LINEAR16`. `FLAC` // stream // encoding supports 16-bit and 24-bit samples, however, not all fields // in // `STREAMINFO` are supported. // "MULAW" - 8-bit samples that compand 14-bit audio samples using // G.711 PCMU/mu-law. // "AMR" - Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` // must be 8000. // "AMR_WB" - Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` // must be 16000. // "OGG_OPUS" - Opus encoded audio frames in Ogg // container // ([OggOpus](https://wiki.xiph.org/OggOpus)). // `sample_rate_her // tz` must be one of 8000, 12000, 16000, 24000, or 48000. // "SPEEX_WITH_HEADER_BYTE" - Although the use of lossy encodings is // not recommended, if a very low // bitrate encoding is required, `OGG_OPUS` is highly preferred // over // Speex encoding. The [Speex](https://speex.org/) encoding supported // by // Cloud Speech API has a header byte in each block, as in MIME // type // `audio/x-speex-with-header-byte`. // It is a variant of the RTP Speex encoding defined in // [RFC 5574](https://tools.ietf.org/html/rfc5574). // The stream is a sequence of blocks, one block per RTP packet. Each // block // starts with a byte containing the length of the block, in bytes, // followed // by one or more frames of Speex data, padded to an integral number // of // bytes (octets) as specified in RFC 5574. In other words, each RTP // header // is replaced with a single byte containing the block length. Only // Speex // wideband is supported. `sample_rate_hertz` must be 16000. // "MP3" - MP3 audio. Support all standard MP3 bitrates (which range // from 32-320 // kbps). When using this encoding, `sample_rate_hertz` has to match // the // sample rate of the file being used. Encoding string `json:"encoding,omitempty"` // LanguageCode: Required. The language of the supplied audio as // a // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language // tag. // Example: "en-US". // See // [Language // Support](https://cloud.google.com/speech-to-text/docs/langua // ges) for a list // of the currently supported language codes. LanguageCode string `json:"languageCode,omitempty"` // MaxAlternatives: Maximum number of recognition hypotheses to be // returned. // Specifically, the maximum number of `SpeechRecognitionAlternative` // messages // within each `SpeechRecognitionResult`. // The server may return fewer than `max_alternatives`. // Valid values are `0`-`30`. A value of `0` or `1` will return a // maximum of // one. If omitted, will return a maximum of one. MaxAlternatives int64 `json:"maxAlternatives,omitempty"` // Metadata: Metadata regarding this request. Metadata *RecognitionMetadata `json:"metadata,omitempty"` // Model: Which model to select for the given request. Select the // model // best suited to your domain to get best results. If a model is // not // explicitly specified, then we auto-select a model based on the // parameters // in the RecognitionConfig. // <table> // <tr> // <td><b>Model</b></td> // <td><b>Description</b></td> // </tr> // <tr> // <td><code>command_and_search</code></td> // <td>Best for short queries such as voice commands or voice // search.</td> // </tr> // <tr> // <td><code>phone_call</code></td> // <td>Best for audio that originated from a phone call (typically // recorded at an 8khz sampling rate).</td> // </tr> // <tr> // <td><code>video</code></td> // <td>Best for audio that originated from from video or includes // multiple // speakers. Ideally the audio is recorded at a 16khz or // greater // sampling rate. This is a premium model that costs more than // the // standard rate.</td> // </tr> // <tr> // <td><code>default</code></td> // <td>Best for audio that is not one of the specific audio models. // For example, long-form audio. Ideally the audio is // high-fidelity, // recorded at a 16khz or greater sampling rate.</td> // </tr> // </table> Model string `json:"model,omitempty"` // ProfanityFilter: If set to `true`, the server will attempt to filter // out // profanities, replacing all but the initial character in each filtered // word // with asterisks, e.g. "f***". If set to `false` or omitted, // profanities // won't be filtered out. ProfanityFilter bool `json:"profanityFilter,omitempty"` // SampleRateHertz: Sample rate in Hertz of the audio data sent in // all // `RecognitionAudio` messages. Valid values are: 8000-48000. // 16000 is optimal. For best results, set the sampling rate of the // audio // source to 16000 Hz. If that's not possible, use the native sample // rate of // the audio source (instead of re-sampling). // This field is optional for FLAC and WAV audio files, but is // required for all other audio formats. For details, see AudioEncoding. SampleRateHertz int64 `json:"sampleRateHertz,omitempty"` // SpeechContexts: Array of SpeechContext. // A means to provide context to assist the speech recognition. For // more // information, // see // [speech // adaptation](https://cloud.google.com/speech-to-text/docs/c // ontext-strength). SpeechContexts []*SpeechContext `json:"speechContexts,omitempty"` // UseEnhanced: Set to true to use an enhanced model for speech // recognition. // If `use_enhanced` is set to true and the `model` field is not set, // then // an appropriate enhanced model is chosen if an enhanced model exists // for // the audio. // // If `use_enhanced` is true and an enhanced version of the specified // model // does not exist, then the speech is recognized using the standard // version // of the specified model. UseEnhanced bool `json:"useEnhanced,omitempty"` // ForceSendFields is a list of field names (e.g. "Adaptation") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Adaptation") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
RecognitionConfig: Provides information to the recognizer that specifies how to process the request.
func (*RecognitionConfig) MarshalJSON ¶
func (s *RecognitionConfig) MarshalJSON() ([]byte, error)
type RecognitionMetadata ¶
type RecognitionMetadata struct { // AudioTopic: Description of the content. Eg. "Recordings of federal // supreme court // hearings from 2012". AudioTopic string `json:"audioTopic,omitempty"` // IndustryNaicsCodeOfAudio: The industry vertical to which this speech // recognition request most // closely applies. This is most indicative of the topics contained // in the audio. Use the 6-digit NAICS code to identify the // industry // vertical - see https://www.naics.com/search/. IndustryNaicsCodeOfAudio int64 `json:"industryNaicsCodeOfAudio,omitempty"` // InteractionType: The use case most closely describing the audio // content to be recognized. // // Possible values: // "INTERACTION_TYPE_UNSPECIFIED" - Use case is either unknown or is // something other than one of the other // values below. // "DISCUSSION" - Multiple people in a conversation or discussion. For // example in a // meeting with two or more people actively participating. Typically // all the primary people speaking would be in the same room (if // not, // see PHONE_CALL) // "PRESENTATION" - One or more persons lecturing or presenting to // others, mostly // uninterrupted. // "PHONE_CALL" - A phone-call or video-conference in which two or // more people, who are // not in the same room, are actively participating. // "VOICEMAIL" - A recorded message intended for another person to // listen to. // "PROFESSIONALLY_PRODUCED" - Professionally produced audio (eg. TV // Show, Podcast). // "VOICE_SEARCH" - Transcribe spoken questions and queries into text. // "VOICE_COMMAND" - Transcribe voice commands, such as for // controlling a device. // "DICTATION" - Transcribe speech to text to create a written // document, such as a // text-message, email or report. InteractionType string `json:"interactionType,omitempty"` // MicrophoneDistance: The audio type that most closely describes the // audio being recognized. // // Possible values: // "MICROPHONE_DISTANCE_UNSPECIFIED" - Audio type is not known. // "NEARFIELD" - The audio was captured from a closely placed // microphone. Eg. phone, // dictaphone, or handheld microphone. Generally if there speaker is // within // 1 meter of the microphone. // "MIDFIELD" - The speaker if within 3 meters of the microphone. // "FARFIELD" - The speaker is more than 3 meters away from the // microphone. MicrophoneDistance string `json:"microphoneDistance,omitempty"` // ObfuscatedId: Obfuscated (privacy-protected) ID of the user, to // identify number of // unique users using the service. ObfuscatedId int64 `json:"obfuscatedId,omitempty,string"` // OriginalMediaType: The original media the speech was recorded on. // // Possible values: // "ORIGINAL_MEDIA_TYPE_UNSPECIFIED" - Unknown original media type. // "AUDIO" - The speech data is an audio recording. // "VIDEO" - The speech data originally recorded on a video. OriginalMediaType string `json:"originalMediaType,omitempty"` // OriginalMimeType: Mime type of the original audio file. For example // `audio/m4a`, // `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`. // A list of possible audio mime types is maintained // at // http://www.iana.org/assignments/media-types/media-types.xhtml#audio OriginalMimeType string `json:"originalMimeType,omitempty"` // RecordingDeviceName: The device used to make the recording. Examples // 'Nexus 5X' or // 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or // 'Cardioid Microphone'. RecordingDeviceName string `json:"recordingDeviceName,omitempty"` // RecordingDeviceType: The type of device the speech was recorded with. // // Possible values: // "RECORDING_DEVICE_TYPE_UNSPECIFIED" - The recording device is // unknown. // "SMARTPHONE" - Speech was recorded on a smartphone. // "PC" - Speech was recorded using a personal computer or tablet. // "PHONE_LINE" - Speech was recorded over a phone line. // "VEHICLE" - Speech was recorded in a vehicle. // "OTHER_OUTDOOR_DEVICE" - Speech was recorded outdoors. // "OTHER_INDOOR_DEVICE" - Speech was recorded indoors. RecordingDeviceType string `json:"recordingDeviceType,omitempty"` // ForceSendFields is a list of field names (e.g. "AudioTopic") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "AudioTopic") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
RecognitionMetadata: Description of audio data to be recognized.
func (*RecognitionMetadata) MarshalJSON ¶
func (s *RecognitionMetadata) MarshalJSON() ([]byte, error)
type RecognizeRequest ¶
type RecognizeRequest struct { // Audio: Required. The audio data to be recognized. Audio *RecognitionAudio `json:"audio,omitempty"` // Config: Required. Provides information to the recognizer that // specifies how to // process the request. Config *RecognitionConfig `json:"config,omitempty"` // ForceSendFields is a list of field names (e.g. "Audio") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Audio") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
RecognizeRequest: The top-level message sent by the client for the `Recognize` method.
func (*RecognizeRequest) MarshalJSON ¶
func (s *RecognizeRequest) MarshalJSON() ([]byte, error)
type RecognizeResponse ¶
type RecognizeResponse struct { // Results: Sequential list of transcription results corresponding // to // sequential portions of audio. Results []*SpeechRecognitionResult `json:"results,omitempty"` // ServerResponse contains the HTTP response code and headers from the // server. googleapi.ServerResponse `json:"-"` // ForceSendFields is a list of field names (e.g. "Results") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Results") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
RecognizeResponse: The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages.
func (*RecognizeResponse) MarshalJSON ¶
func (s *RecognizeResponse) MarshalJSON() ([]byte, error)
type Service ¶
type Service struct { BasePath string // API endpoint base URL UserAgent string // optional additional User-Agent fragment Operations *OperationsService Projects *ProjectsService Speech *SpeechService // contains filtered or unexported fields }
func New
deprecated
New creates a new Service. It uses the provided http.Client for requests.
Deprecated: please use NewService instead. To provide a custom HTTP client, use option.WithHTTPClient. If you are using google.golang.org/api/googleapis/transport.APIKey, use option.WithAPIKey with NewService instead.
func NewService ¶ added in v0.3.0
NewService creates a new Service.
type SpeakerDiarizationConfig ¶
type SpeakerDiarizationConfig struct { // EnableSpeakerDiarization: If 'true', enables speaker detection for // each recognized word in // the top alternative of the recognition result using a speaker_tag // provided // in the WordInfo. EnableSpeakerDiarization bool `json:"enableSpeakerDiarization,omitempty"` // MaxSpeakerCount: Maximum number of speakers in the conversation. This // range gives you more // flexibility by allowing the system to automatically determine the // correct // number of speakers. If not set, the default value is 6. MaxSpeakerCount int64 `json:"maxSpeakerCount,omitempty"` // MinSpeakerCount: Minimum number of speakers in the conversation. This // range gives you more // flexibility by allowing the system to automatically determine the // correct // number of speakers. If not set, the default value is 2. MinSpeakerCount int64 `json:"minSpeakerCount,omitempty"` // SpeakerTag: Output only. Unused. SpeakerTag int64 `json:"speakerTag,omitempty"` // ForceSendFields is a list of field names (e.g. // "EnableSpeakerDiarization") to unconditionally include in API // requests. By default, fields with empty values are omitted from API // requests. However, any non-pointer, non-interface field appearing in // ForceSendFields will be sent to the server regardless of whether the // field is empty or not. This may be used to include empty fields in // Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "EnableSpeakerDiarization") // to include in API requests with the JSON null value. By default, // fields with empty values are omitted from API requests. However, any // field with an empty value appearing in NullFields will be sent to the // server as null. It is an error if a field in this list has a // non-empty value. This may be used to include null fields in Patch // requests. NullFields []string `json:"-"` }
SpeakerDiarizationConfig: Config to enable speaker diarization.
func (*SpeakerDiarizationConfig) MarshalJSON ¶
func (s *SpeakerDiarizationConfig) MarshalJSON() ([]byte, error)
type SpeechAdaptation ¶ added in v0.23.0
type SpeechAdaptation struct { // CustomClasses: A collection of custom classes. To specify the classes // inline, leave the // class' `name` blank and fill in the rest of its fields, giving it a // unique // `custom_class_id`. Refer to the inline defined class in phrase hints // by its // `custom_class_id`. CustomClasses []*CustomClass `json:"customClasses,omitempty"` // PhraseSets: A collection of phrase sets. To specify the hints inline, // leave the // phrase set's `name` blank and fill in the rest of its fields. // Any // phrase set can use any custom class. PhraseSets []*PhraseSet `json:"phraseSets,omitempty"` // ForceSendFields is a list of field names (e.g. "CustomClasses") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "CustomClasses") to include // in API requests with the JSON null value. By default, fields with // empty values are omitted from API requests. However, any field with // an empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
SpeechAdaptation: Speech adaptation configuration.
func (*SpeechAdaptation) MarshalJSON ¶ added in v0.23.0
func (s *SpeechAdaptation) MarshalJSON() ([]byte, error)
type SpeechContext ¶
type SpeechContext struct { // Boost: Hint Boost. Positive value will increase the probability that // a specific // phrase will be recognized over other similar sounding phrases. The // higher // the boost, the higher the chance of false positive recognition as // well. // Negative boost values would correspond to anti-biasing. Anti-biasing // is not // enabled, so negative boost will simply be ignored. Though `boost` // can // accept a wide range of positive values, most use cases are best // served with // values between 0 and 20. We recommend using a binary search approach // to // finding the optimal value for your use case. Boost float64 `json:"boost,omitempty"` // Phrases: A list of strings containing words and phrases "hints" so // that // the speech recognition is more likely to recognize them. This can be // used // to improve the accuracy for specific words and phrases, for example, // if // specific commands are typically spoken by the user. This can also be // used // to add additional words to the vocabulary of the recognizer. // See // [usage // limits](https://cloud.google.com/speech-to-text/quotas#content). // // List // items can also be set to classes for groups of words that // represent // common concepts that occur in natural language. For example, rather // than // providing phrase hints for every month of the year, using the $MONTH // class // improves the likelihood of correctly transcribing audio that // includes // months. Phrases []string `json:"phrases,omitempty"` // ForceSendFields is a list of field names (e.g. "Boost") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Boost") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
SpeechContext: Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
func (*SpeechContext) MarshalJSON ¶
func (s *SpeechContext) MarshalJSON() ([]byte, error)
func (*SpeechContext) UnmarshalJSON ¶ added in v0.6.0
func (s *SpeechContext) UnmarshalJSON(data []byte) error
type SpeechLongrunningrecognizeCall ¶
type SpeechLongrunningrecognizeCall struct {
// contains filtered or unexported fields
}
func (*SpeechLongrunningrecognizeCall) Context ¶
func (c *SpeechLongrunningrecognizeCall) Context(ctx context.Context) *SpeechLongrunningrecognizeCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*SpeechLongrunningrecognizeCall) Do ¶
func (c *SpeechLongrunningrecognizeCall) Do(opts ...googleapi.CallOption) (*Operation, error)
Do executes the "speech.speech.longrunningrecognize" call. Exactly one of *Operation or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *Operation.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*SpeechLongrunningrecognizeCall) Fields ¶
func (c *SpeechLongrunningrecognizeCall) Fields(s ...googleapi.Field) *SpeechLongrunningrecognizeCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*SpeechLongrunningrecognizeCall) Header ¶
func (c *SpeechLongrunningrecognizeCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
type SpeechRecognitionAlternative ¶
type SpeechRecognitionAlternative struct { // Confidence: The confidence estimate between 0.0 and 1.0. A higher // number // indicates an estimated greater likelihood that the recognized words // are // correct. This field is set only for the top alternative of a // non-streaming // result or, of a streaming result where `is_final=true`. // This field is not guaranteed to be accurate and users should not rely // on it // to be always provided. // The default of 0.0 is a sentinel value indicating `confidence` was // not set. Confidence float64 `json:"confidence,omitempty"` // Transcript: Transcript text representing the words that the user // spoke. Transcript string `json:"transcript,omitempty"` // Words: A list of word-specific information for each recognized // word. // Note: When `enable_speaker_diarization` is true, you will see all the // words // from the beginning of the audio. Words []*WordInfo `json:"words,omitempty"` // ForceSendFields is a list of field names (e.g. "Confidence") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Confidence") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
SpeechRecognitionAlternative: Alternative hypotheses (a.k.a. n-best list).
func (*SpeechRecognitionAlternative) MarshalJSON ¶
func (s *SpeechRecognitionAlternative) MarshalJSON() ([]byte, error)
func (*SpeechRecognitionAlternative) UnmarshalJSON ¶
func (s *SpeechRecognitionAlternative) UnmarshalJSON(data []byte) error
type SpeechRecognitionResult ¶
type SpeechRecognitionResult struct { // Alternatives: May contain one or more recognition hypotheses (up to // the // maximum specified in `max_alternatives`). // These alternatives are ordered in terms of accuracy, with the top // (first) // alternative being the most probable, as ranked by the recognizer. Alternatives []*SpeechRecognitionAlternative `json:"alternatives,omitempty"` // ChannelTag: For multi-channel audio, this is the channel number // corresponding to the // recognized result for the audio from that channel. // For audio_channel_count = N, its output values can range from '1' to // 'N'. ChannelTag int64 `json:"channelTag,omitempty"` // LanguageCode: Output only. The // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language // tag // of the language in this result. This language code was detected to // have // the most likelihood of being spoken in the audio. LanguageCode string `json:"languageCode,omitempty"` // ForceSendFields is a list of field names (e.g. "Alternatives") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Alternatives") to include // in API requests with the JSON null value. By default, fields with // empty values are omitted from API requests. However, any field with // an empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
SpeechRecognitionResult: A speech recognition result corresponding to a portion of the audio.
func (*SpeechRecognitionResult) MarshalJSON ¶
func (s *SpeechRecognitionResult) MarshalJSON() ([]byte, error)
type SpeechRecognizeCall ¶
type SpeechRecognizeCall struct {
// contains filtered or unexported fields
}
func (*SpeechRecognizeCall) Context ¶
func (c *SpeechRecognizeCall) Context(ctx context.Context) *SpeechRecognizeCall
Context sets the context to be used in this call's Do method. Any pending HTTP request will be aborted if the provided context is canceled.
func (*SpeechRecognizeCall) Do ¶
func (c *SpeechRecognizeCall) Do(opts ...googleapi.CallOption) (*RecognizeResponse, error)
Do executes the "speech.speech.recognize" call. Exactly one of *RecognizeResponse or error will be non-nil. Any non-2xx status code is an error. Response headers are in either *RecognizeResponse.ServerResponse.Header or (if a response was returned at all) in error.(*googleapi.Error).Header. Use googleapi.IsNotModified to check whether the returned error was because http.StatusNotModified was returned.
func (*SpeechRecognizeCall) Fields ¶
func (c *SpeechRecognizeCall) Fields(s ...googleapi.Field) *SpeechRecognizeCall
Fields allows partial responses to be retrieved. See https://developers.google.com/gdata/docs/2.0/basics#PartialResponse for more information.
func (*SpeechRecognizeCall) Header ¶
func (c *SpeechRecognizeCall) Header() http.Header
Header returns an http.Header that can be modified by the caller to add HTTP headers to the request.
type SpeechService ¶
type SpeechService struct {
// contains filtered or unexported fields
}
func NewSpeechService ¶
func NewSpeechService(s *Service) *SpeechService
func (*SpeechService) Longrunningrecognize ¶
func (r *SpeechService) Longrunningrecognize(longrunningrecognizerequest *LongRunningRecognizeRequest) *SpeechLongrunningrecognizeCall
Longrunningrecognize: Performs asynchronous speech recognition: receive results via the google.longrunning.Operations interface. Returns either an `Operation.error` or an `Operation.response` which contains a `LongRunningRecognizeResponse` message. For more information on asynchronous speech recognition, see the [how-to](https://cloud.google.com/speech-to-text/docs/async-recogn ize).
func (*SpeechService) Recognize ¶
func (r *SpeechService) Recognize(recognizerequest *RecognizeRequest) *SpeechRecognizeCall
Recognize: Performs synchronous speech recognition: receive results after all audio has been sent and processed.
type Status ¶
type Status struct { // Code: The status code, which should be an enum value of // google.rpc.Code. Code int64 `json:"code,omitempty"` // Details: A list of messages that carry the error details. There is a // common set of // message types for APIs to use. Details []googleapi.RawMessage `json:"details,omitempty"` // Message: A developer-facing error message, which should be in // English. Any // user-facing error message should be localized and sent in // the // google.rpc.Status.details field, or localized by the client. Message string `json:"message,omitempty"` // ForceSendFields is a list of field names (e.g. "Code") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Code") to include in API // requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
Status: The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details.
You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).
func (*Status) MarshalJSON ¶
type WordInfo ¶
type WordInfo struct { // Confidence: The confidence estimate between 0.0 and 1.0. A higher // number // indicates an estimated greater likelihood that the recognized words // are // correct. This field is set only for the top alternative of a // non-streaming // result or, of a streaming result where `is_final=true`. // This field is not guaranteed to be accurate and users should not rely // on it // to be always provided. // The default of 0.0 is a sentinel value indicating `confidence` was // not set. Confidence float64 `json:"confidence,omitempty"` // EndTime: Time offset relative to the beginning of the audio, // and corresponding to the end of the spoken word. // This field is only set if `enable_word_time_offsets=true` and only // in the top hypothesis. // This is an experimental feature and the accuracy of the time offset // can // vary. EndTime string `json:"endTime,omitempty"` // SpeakerTag: Output only. A distinct integer value is assigned for // every speaker within // the audio. This field specifies which one of those speakers was // detected to // have spoken this word. Value ranges from '1' to // diarization_speaker_count. // speaker_tag is set if enable_speaker_diarization = 'true' and only in // the // top alternative. SpeakerTag int64 `json:"speakerTag,omitempty"` // StartTime: Time offset relative to the beginning of the audio, // and corresponding to the start of the spoken word. // This field is only set if `enable_word_time_offsets=true` and only // in the top hypothesis. // This is an experimental feature and the accuracy of the time offset // can // vary. StartTime string `json:"startTime,omitempty"` // Word: The word corresponding to this set of information. Word string `json:"word,omitempty"` // ForceSendFields is a list of field names (e.g. "Confidence") to // unconditionally include in API requests. By default, fields with // empty values are omitted from API requests. However, any non-pointer, // non-interface field appearing in ForceSendFields will be sent to the // server regardless of whether the field is empty or not. This may be // used to include empty fields in Patch requests. ForceSendFields []string `json:"-"` // NullFields is a list of field names (e.g. "Confidence") to include in // API requests with the JSON null value. By default, fields with empty // values are omitted from API requests. However, any field with an // empty value appearing in NullFields will be sent to the server as // null. It is an error if a field in this list has a non-empty value. // This may be used to include null fields in Patch requests. NullFields []string `json:"-"` }
WordInfo: Word-specific information for recognized words.