Package google.cloud.speech.v1

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

Requires the following OAuth scope:

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

For more information, see the Auth Guide.

Recognize

rpc Recognize(RecognizeRequest) returns (RecognizeResponse)

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

Authorization

Requires the following OAuth scope:

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

For more information, see the Auth Guide.

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

Requires the following OAuth scope:

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

For more information, see the Auth Guide.

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.

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

Required Encoding of audio data sent in all RecognitionAudio messages.

sample_rate_hertz

int32

Required 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).

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.

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.

AudioEncoding

Audio encoding of the data sent in the audio message. All encodings support only 1 channel (mono) audio. Only FLAC includes a header that describes the bytes of audio that follow the header. The other encodings are raw audio bytes with no header.

For best results, the audio source should be captured and transmitted using a lossless encoding (FLAC or LINEAR16). Recognition accuracy may be reduced if lossy codecs, which include the other codecs listed in this section, are used to capture or transmit the audio, particularly if background noise is present.

Enums
ENCODING_UNSPECIFIED Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.
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 16000.
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.

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 typically provided only for the top hypothesis, and only for is_final=true results. Clients should not rely on the confidence field as it is not guaranteed to be accurate, or even set, in any of the results. The default of 0.0 is a sentinel value indicating confidence was not set.

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).

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).

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.

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.

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 one or more StreamingRecognizeResponse 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. speech_event_type: END_OF_SINGLE_UTTERANCE

  8. 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 #8 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.

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.

Send feedback about...

Google Cloud Speech API