Package google.cloud.texttospeech.v1beta1

Index

TextToSpeech

Service that implements Google Cloud Text-to-Speech API.

ListVoices

rpc ListVoices(ListVoicesRequest) returns (ListVoicesResponse)

Returns a list of Voice supported for synthesis.

Authorization scopes

Requires the following OAuth scope:

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

For more information, see the Authentication Overview.

StreamingSynthesize

rpc StreamingSynthesize(StreamingSynthesizeRequest) returns (StreamingSynthesizeResponse)

Performs bidirectional streaming speech synthesis: receive audio while sending text.

Authorization scopes

Requires the following OAuth scope:

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

For more information, see the Authentication Overview.

SynthesizeSpeech

rpc SynthesizeSpeech(SynthesizeSpeechRequest) returns (SynthesizeSpeechResponse)

Synthesizes speech synchronously: receive results after all text input has been processed.

Authorization scopes

Requires the following OAuth scope:

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

For more information, see the Authentication Overview.

TextToSpeechLongAudioSynthesize

Service that implements Google Cloud Text-to-Speech API.

SynthesizeLongAudio

rpc SynthesizeLongAudio(SynthesizeLongAudioRequest) returns (Operation)

Synthesizes long form text asynchronously.

Authorization scopes

Requires the following OAuth scope:

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

For more information, see the Authentication Overview.

AudioConfig

Description of audio data to be synthesized.

Fields
audio_encoding

AudioEncoding

Required. The format of the audio byte stream.

speaking_rate

double

Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any other values < 0.25 or > 4.0 will return an error.

pitch

double

Optional. Input only. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch.

volume_gain_db

double

Optional. Input only. Volume gain (in dB) of the normal native volume supported by the specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB) will play at approximately half the amplitude of the normal native signal amplitude. A value of +6.0 (dB) will play at approximately twice the amplitude of the normal native signal amplitude. Strongly recommend not to exceed +10 (dB) as there's usually no effective increase in loudness for any value greater than that.

sample_rate_hertz

int32

Optional. The synthesis sample rate (in hertz) for this audio. When this is specified in SynthesizeSpeechRequest, if this is different from the voice's natural sample rate, then the synthesizer will honor this request by converting to the desired sample rate (which might result in worse audio quality), unless the specified sample rate is not supported for the encoding chosen, in which case it will fail the request and return google.rpc.Code.INVALID_ARGUMENT.

effects_profile_id[]

string

Optional. Input only. An identifier which selects 'audio effects' profiles that are applied on (post synthesized) text to speech. Effects are applied on top of each other in the order they are given. See audio profiles for current supported profile ids.

AudioEncoding

Configuration to set up audio encoder. The encoding determines the output audio format that we'd like.

Enums
AUDIO_ENCODING_UNSPECIFIED Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.
LINEAR16 Uncompressed 16-bit signed little-endian samples (Linear PCM). Audio content returned as LINEAR16 also contains a WAV header.
MP3 MP3 audio at 32kbps.
MP3_64_KBPS MP3 at 64kbps.
OGG_OPUS Opus encoded audio wrapped in an ogg container. The result will be a file which can be played natively on Android, and in browsers (at least Chrome and Firefox). The quality of the encoding is considerably higher than MP3 while using approximately the same bitrate.
MULAW 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law. Audio content returned as MULAW also contains a WAV header.
ALAW 8-bit samples that compand 14-bit audio samples using G.711 PCMU/A-law. Audio content returned as ALAW also contains a WAV header.

CustomVoiceParams

Description of the custom voice to be synthesized.

Fields
model

string

Required. The name of the AutoML model that synthesizes the custom voice.

reported_usage
(deprecated)

ReportedUsage

Optional. Deprecated. The usage of the synthesized audio to be reported.

ReportedUsage

Deprecated. The usage of the synthesized audio. Usage does not affect billing.

Enums
REPORTED_USAGE_UNSPECIFIED Request with reported usage unspecified will be rejected.
REALTIME For scenarios where the synthesized audio is not downloadable and can only be used once. For example, real-time request in IVR system.
OFFLINE For scenarios where the synthesized audio is downloadable and can be reused. For example, the synthesized audio is downloaded, stored in customer service system and played repeatedly.

ListVoicesRequest

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

Fields
language_code

string

Optional. Recommended. BCP-47 language tag. If not specified, the API will return all supported voices. If specified, the ListVoices call will only return voices that can be used to synthesize this language_code. For example, if you specify "en-NZ", all "en-NZ" voices will be returned. If you specify "no", both "no-\*" (Norwegian) and "nb-\*" (Norwegian Bokmal) voices will be returned.

ListVoicesResponse

The message returned to the client by the ListVoices method.

Fields
voices[]

Voice

The list of voices.

SsmlVoiceGender

Gender of the voice as described in SSML voice element.

Enums
SSML_VOICE_GENDER_UNSPECIFIED An unspecified gender. In VoiceSelectionParams, this means that the client doesn't care which gender the selected voice will have. In the Voice field of ListVoicesResponse, this may mean that the voice doesn't fit any of the other categories in this enum, or that the gender of the voice isn't known.
MALE A male voice.
FEMALE A female voice.
NEUTRAL A gender-neutral voice. This voice is not yet supported.

StreamingSynthesisInput

Input to be synthesized.

Fields

Union field input_source.

input_source can be only one of the following:

text

string

The raw text to be synthesized. Each input containing complete, terminating sentences will likely result in better prosody in the output audio. That said, users may input text as desired.

StreamingSynthesizeConfig

Provides configuration information for the StreamingSynthesize request.

Fields
voice

VoiceSelectionParams

Required. The desired voice of the synthesized audio.

StreamingSynthesizeRequest

Request message for the StreamingSynthesize method. Multiple StreamingSynthesizeRequest messages are sent in one call. The first message must contain a streaming_config that fully specifies the request configuration and must not contain input. All subsequent messages must only have input set.

Fields
Union field streaming_request. The request to be sent, either a StreamingSynthesizeConfig or StreamingSynthesisInput. streaming_request can be only one of the following:
streaming_config

StreamingSynthesizeConfig

StreamingSynthesizeConfig to be used in this streaming attempt. Only specified in the first message sent in a StreamingSynthesize call.

input

StreamingSynthesisInput

Input to synthesize. Specified in all messages but the first in a StreamingSynthesize call.

StreamingSynthesizeResponse

StreamingSynthesizeResponse is the only message returned to the client by StreamingSynthesize method. A series of zero or more StreamingSynthesizeResponse messages are streamed back to the client.

Fields
audio_content

bytes

The audio data bytes encoded as specified in the request. This is headerless LINEAR16 audio with a sample rate of 24000.

SynthesisInput

Contains text input to be synthesized. Either text or ssml must be supplied. Supplying both or neither returns google.rpc.Code.INVALID_ARGUMENT. The input size is limited to 5000 bytes.

Fields
Union field input_source. The input source, which is either plain text or SSML. input_source can be only one of the following:
text

string

The raw text to be synthesized.

ssml

string

The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return google.rpc.Code.INVALID_ARGUMENT. For more information, see SSML.

SynthesizeLongAudioMetadata

Metadata for response returned by the SynthesizeLongAudio method.

Fields
start_time

Timestamp

Time when the request was received.

last_update_time
(deprecated)

Timestamp

Deprecated. Do not use.

progress_percentage

double

The progress of the most recent processing update in percentage, ie. 70.0%.

SynthesizeLongAudioRequest

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

Fields
parent

string

The resource states of the request in the form of projects/*/locations/*.

input

SynthesisInput

Required. The Synthesizer requires either plain text or SSML as input.

audio_config

AudioConfig

Required. The configuration of the synthesized audio.

output_gcs_uri

string

Required. Specifies a Cloud Storage URI for the synthesis results. Must be specified in the format: gs://bucket_name/object_name, and the bucket must already exist.

voice

VoiceSelectionParams

Required. The desired voice of the synthesized audio.

SynthesizeLongAudioResponse

This type has no fields.

The message returned to the client by the SynthesizeLongAudio method.

SynthesizeSpeechRequest

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

Fields
input

SynthesisInput

Required. The Synthesizer requires either plain text or SSML as input.

voice

VoiceSelectionParams

Required. The desired voice of the synthesized audio.

audio_config

AudioConfig

Required. The configuration of the synthesized audio.

enable_time_pointing[]

TimepointType

Whether and what timepoints are returned in the response.

TimepointType

The type of timepoint information that is returned in the response.

Enums
TIMEPOINT_TYPE_UNSPECIFIED Not specified. No timepoint information will be returned.
SSML_MARK Timepoint information of <mark> tags in SSML input will be returned.

SynthesizeSpeechResponse

The message returned to the client by the SynthesizeSpeech method.

Fields
audio_content

bytes

The audio data bytes encoded as specified in the request, including the header for encodings that are wrapped in containers (e.g. MP3, OGG_OPUS). For LINEAR16 audio, we include the WAV header. Note: as with all bytes fields, protobuffers use a pure binary representation, whereas JSON representations use base64.

timepoints[]

Timepoint

A link between a position in the original request input and a corresponding time in the output audio. It's only supported via <mark> of SSML input.

audio_config

AudioConfig

The audio metadata of audio_content.

Timepoint

This contains a mapping between a certain point in the input text and a corresponding time in the output audio.

Fields
mark_name

string

Timepoint name as received from the client within <mark> tag.

time_seconds

double

Time offset in seconds from the start of the synthesized audio.

Voice

Description of a voice supported by the TTS service.

Fields
language_codes[]

string

The languages that this voice supports, expressed as BCP-47 language tags (e.g. "en-US", "es-419", "cmn-tw").

name

string

The name of this voice. Each distinct voice has a unique name.

ssml_gender

SsmlVoiceGender

The gender of this voice.

natural_sample_rate_hertz

int32

The natural sample rate (in hertz) for this voice.

VoiceCloneParams

The configuration of Voice Clone feature.

Fields
voice_cloning_key

string

Required. Created by GenerateVoiceCloningKey.

VoiceSelectionParams

Description of which voice to use for a synthesis request.

Fields
language_code

string

Required. The language (and potentially also the region) of the voice expressed as a BCP-47 language tag, e.g. "en-US". This should not include a script tag (e.g. use "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred from the input provided in the SynthesisInput. The TTS service will use this parameter to help choose an appropriate voice. Note that the TTS service may choose a voice with a slightly different language code than the one selected; it may substitute a different region (e.g. using en-US rather than en-CA if there isn't a Canadian voice available), or even a different language, e.g. using "nb" (Norwegian Bokmal) instead of "no" (Norwegian)".

name

string

The name of the voice. If both the name and the gender are not set, the service will choose a voice based on the other parameters such as language_code.

ssml_gender

SsmlVoiceGender

The preferred gender of the voice. If not set, the service will choose a voice based on the other parameters such as language_code and name. Note that this is only a preference, not requirement; if a voice of the appropriate gender is not available, the synthesizer should substitute a voice with a different gender rather than failing the request.

custom_voice

CustomVoiceParams

The configuration for a custom voice. If [CustomVoiceParams.model] is set, the service will choose the custom voice matching the specified configuration.

voice_clone

VoiceCloneParams

The configuration for a voice clone. If [VoiceCloneParams.voice_clone_key] is set, the service will choose the voice clone matching the specified configuration.