Package google.cloud.speech.v1p1beta1

Index

Speech

Service that implements Google Cloud Speech API.

LongRunningRecognize

rpc LongRunningRecognize(LongRunningRecognizeRequest) returns (Operation)

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.

Authorization Scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

Recognize

rpc Recognize(RecognizeRequest) returns (RecognizeResponse)

Performs synchronous speech recognition: receive results after all audio has been sent and processed.

Authorization Scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

StreamingRecognize

rpc StreamingRecognize(StreamingRecognizeRequest) returns (StreamingRecognizeResponse)

Performs bidirectional streaming speech recognition: receive results while sending audio. This method is only available via the gRPC API (not REST).

Authorization Scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

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.

Fields
progress_percent

int32

Approximate percentage of audio processed thus far. Guaranteed to be 100 when the audio is fully processed and the results are available.

start_time

Timestamp

Time when the request was received.

last_update_time

Timestamp

Time of the most recent processing update.

LongRunningRecognizeRequest

The top-level message sent by the client for the LongRunningRecognize method.

Fields
config

RecognitionConfig

Required Provides information to the recognizer that specifies how to process the request.

audio

RecognitionAudio

Required The audio data to be recognized.

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.

Fields
results[]

SpeechRecognitionResult

Output only. Sequential list of transcription results corresponding to sequential portions of audio.

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 audio limits.

Fields
Union field audio_source. The audio source, which is either inline content or a Google Cloud Storage uri. audio_source can be only one of the following:
content

bytes

The audio data bytes encoded as specified in RecognitionConfig. Note: as with all bytes fields, protobuffers use a pure binary representation, whereas JSON representations use base64.

uri

string

URI that points to a file that contains audio data bytes as specified in RecognitionConfig. 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.

RecognitionConfig

Provides information to the recognizer that specifies how to process the request.

Fields
encoding

AudioEncoding

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.

sample_rate_hertz

int32

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 and required for all other audio formats. For details, see AudioEncoding.

audio_channel_count

int32

Optional 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'.

enable_separate_recognition_per_channel

bool

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. NOTE: The request is also billed cumulatively for all channels recognized: (audio_channel_count times the audio length)

language_code

string

Required The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.

alternative_language_codes[]

string

Optional A list of up to 3 additional BCP-47 language tags, listing possible alternative languages of the supplied audio. See Language Support 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).

max_alternatives

int32

Optional 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.

profanity_filter

bool

Optional 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.

speech_contexts[]

SpeechContext

Optional A means to provide context to assist the speech recognition.

enable_word_time_offsets

bool

Optional 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.

enable_word_confidence

bool

Optional 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.

enable_automatic_punctuation

bool

Optional 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. NOTE: "This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature."

enable_speaker_diarization

bool

Optional 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: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.

diarization_speaker_count

int32

Optional If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true."

metadata

RecognitionMetadata

Optional Metadata regarding this request.

model

string

Optional 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.

Model Description

command_and_search

Best for short queries such as voice commands or voice search.

phone_call

Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate).

video

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.

default

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.

use_enhanced

bool

Optional Set to true to use an enhanced model for speech recognition. You must also set the model field to a valid, enhanced model. If use_enhanced is set to true and the model field is not set, then use_enhanced is ignored. 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.

Enhanced speech models require that you opt-in to the audio logging using instructions in the alpha documentation. If you set use_enhanced to true and you have not enabled audio logging, then you will receive an error.

AudioEncoding

The encoding of the audio data sent in the request.

All encodings support only 1 channel (mono) audio.

For best results, the audio source should be captured and transmitted using a lossless encoding (FLAC or LINEAR16). The accuracy of the speech recognition can be reduced if lossy codecs are used to capture or transmit audio, particularly if background noise is present. Lossy codecs include MULAW, AMR, AMR_WB, OGG_OPUS, and SPEEX_WITH_HEADER_BYTE.

The FLAC and WAV audio file formats include a header that describes the included audio content. You can request recognition for WAV files that contain either LINEAR16 or MULAW encoded audio. If you send FLAC or WAV audio file format in your request, you do not need to specify an AudioEncoding; the audio encoding format is determined from the file header. If you specify an AudioEncoding when you send send FLAC or WAV audio, the encoding configuration must match the encoding described in the audio header; otherwise the request returns an google.rpc.Code.INVALID_ARGUMENT error code.

Enums
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). sample_rate_hertz 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 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. 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.

RecognitionMetadata

Description of audio data to be recognized.

Fields
interaction_type

InteractionType

The use case most closely describing the audio content to be recognized.

industry_naics_code_of_audio

uint32

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/.

microphone_distance

MicrophoneDistance

The audio type that most closely describes the audio being recognized.

original_media_type

OriginalMediaType

The original media the speech was recorded on.

recording_device_type

RecordingDeviceType

The type of device the speech was recorded with.

recording_device_name

string

The device used to make the recording. Examples 'Nexus 5X' or 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or 'Cardioid Microphone'.

original_mime_type

string

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

obfuscated_id

int64

Obfuscated (privacy-protected) ID of the user, to identify number of unique users using the service.

audio_topic

string

Description of the content. Eg. "Recordings of federal supreme court hearings from 2012".

InteractionType

Use case categories that the audio recognition request can be described by.

Enums
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_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.

MicrophoneDistance

Enumerates the types of capture settings describing an audio file.

Enums
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.

OriginalMediaType

The original media the speech was recorded on.

Enums
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.

RecordingDeviceType

The type of device the speech was recorded with.

Enums
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.

RecognizeRequest

The top-level message sent by the client for the Recognize method.

Fields
config

RecognitionConfig

Required Provides information to the recognizer that specifies how to process the request.

audio

RecognitionAudio

Required The audio data to be recognized.

RecognizeResponse

The only message returned to the client by the Recognize method. It contains the result as zero or more sequential SpeechRecognitionResult messages.

Fields
results[]

SpeechRecognitionResult

Output only. Sequential list of transcription results corresponding to sequential portions of audio.

SpeechContext

Provides "hints" to the speech recognizer to favor specific words and phrases in the results.

Fields
phrases[]

string

Optional 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.

SpeechRecognitionAlternative

Alternative hypotheses (a.k.a. n-best list).

Fields
transcript

string

Output only. Transcript text representing the words that the user spoke.

confidence

float

Output only. 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.

words[]

WordInfo

Output only. 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.

SpeechRecognitionResult

A speech recognition result corresponding to a portion of the audio.

Fields
alternatives[]

SpeechRecognitionAlternative

Output only. 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.

channel_tag

int32

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'.

language_code

string

Output only. The BCP-47 language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.

StreamingRecognitionConfig

Provides information to the recognizer that specifies how to process the request.

Fields
config

RecognitionConfig

Required Provides information to the recognizer that specifies how to process the request.

single_utterance

bool

Optional If false or omitted, the recognizer will perform continuous recognition (continuing to wait for and process audio even if the user pauses speaking) until the client closes the input stream (gRPC API) or until the maximum time limit has been reached. May return multiple StreamingRecognitionResults with the is_final flag set to true.

If true, the recognizer will detect a single spoken utterance. When it detects that the user has paused or stopped speaking, it will return an END_OF_SINGLE_UTTERANCE event and cease recognition. It will return no more than one StreamingRecognitionResult with the is_final flag set to true.

interim_results

bool

Optional If true, interim results (tentative hypotheses) may be returned as they become available (these interim results are indicated with the is_final=false flag). If false or omitted, only is_final=true result(s) are returned.

StreamingRecognitionResult

A streaming speech recognition result corresponding to a portion of the audio that is currently being processed.

Fields
alternatives[]

SpeechRecognitionAlternative

Output only. 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.

is_final

bool

Output only. If false, this StreamingRecognitionResult represents an interim result that may change. If true, this is the final time the speech service will return this particular StreamingRecognitionResult, the recognizer will not return any further hypotheses for this portion of the transcript and corresponding audio.

stability

float

Output only. An estimate of the likelihood that the recognizer will not change its guess about this interim result. Values range from 0.0 (completely unstable) to 1.0 (completely stable). This field is only provided for interim results (is_final=false). The default of 0.0 is a sentinel value indicating stability was not set.

channel_tag

int32

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'.

language_code

string

Output only. The BCP-47 language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.

StreamingRecognizeRequest

The top-level message sent by the client for the StreamingRecognize method. Multiple StreamingRecognizeRequest messages are sent. The first message must contain a streaming_config message and must not contain audio data. All subsequent messages must contain audio data and must not contain a streaming_config message.

Fields
Union field streaming_request. The streaming request, which is either a streaming config or audio content. streaming_request can be only one of the following:
streaming_config

StreamingRecognitionConfig

Provides information to the recognizer that specifies how to process the request. The first StreamingRecognizeRequest message must contain a streaming_config message.

audio_content

bytes

The audio data to be recognized. Sequential chunks of audio data are sent in sequential StreamingRecognizeRequest messages. The first StreamingRecognizeRequest message must not contain audio_content data and all subsequent StreamingRecognizeRequest messages must contain audio_content data. The audio bytes must be encoded as specified in RecognitionConfig. Note: as with all bytes fields, protobuffers use a pure binary representation (not base64). See audio limits.

StreamingRecognizeResponse

StreamingRecognizeResponse is the only message returned to the client by StreamingRecognize. A series of zero or more StreamingRecognizeResponse messages are streamed back to the client. If there is no recognizable audio, and single_utterance is set to false, then no messages are streamed back to the client.

Here's an example of a series of ten StreamingRecognizeResponses that might be returned while processing audio:

  1. results { alternatives { transcript: "tube" } stability: 0.01 }

  2. results { alternatives { transcript: "to be a" } stability: 0.01 }

  3. results { alternatives { transcript: "to be" } stability: 0.9 } results { alternatives { transcript: " or not to be" } stability: 0.01 }

  4. results { alternatives { transcript: "to be or not to be" confidence: 0.92 } alternatives { transcript: "to bee or not to bee" } is_final: true }

  5. results { alternatives { transcript: " that's" } stability: 0.01 }

  6. results { alternatives { transcript: " that is" } stability: 0.9 } results { alternatives { transcript: " the question" } stability: 0.01 }

  7. results { alternatives { transcript: " that is the question" confidence: 0.98 } alternatives { transcript: " that was the question" } is_final: true }

Notes:

  • Only two of the above responses #4 and #7 contain final results; they are indicated by is_final: true. Concatenating these together generates the full transcript: "to be or not to be that is the question".

  • The others contain interim results. #3 and #6 contain two interim results: the first portion has a high stability and is less likely to change; the second portion has a low stability and is very likely to change. A UI designer might choose to show only high stability results.

  • The specific stability and confidence values shown above are only for illustrative purposes. Actual values may vary.

  • In each response, only one of these fields will be set: error, speech_event_type, or one or more (repeated) results.

Fields
error

Status

Output only. If set, returns a google.rpc.Status message that specifies the error for the operation.

results[]

StreamingRecognitionResult

Output only. This repeated list contains zero or more results that correspond to consecutive portions of the audio currently being processed. It contains zero or one is_final=true result (the newly settled portion), followed by zero or more is_final=false results (the interim results).

speech_event_type

SpeechEventType

Output only. Indicates the type of speech event.

SpeechEventType

Indicates the type of speech event.

Enums
SPEECH_EVENT_UNSPECIFIED No speech event specified.
END_OF_SINGLE_UTTERANCE This event indicates that the server has detected the end of the user's speech utterance and expects no additional speech. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection. This event is only sent if single_utterance was set to true, and is not used otherwise.

WordInfo

Word-specific information for recognized words.

Fields
start_time

Duration

Output only. 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.

end_time

Duration

Output only. 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.

word

string

Output only. The word corresponding to this set of information.

confidence

float

Output only. 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.

speaker_tag

int32

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.

このページは役立ちましたか?評価をお願いいたします。

フィードバックを送信...