Index
TextToSpeech
(interface)TextToSpeechLongAudioSynthesize
(interface)AudioConfig
(message)AudioEncoding
(enum)CustomVoiceParams
(message)CustomVoiceParams.ReportedUsage
(enum)ListVoicesRequest
(message)ListVoicesResponse
(message)SsmlVoiceGender
(enum)StreamingSynthesisInput
(message)StreamingSynthesizeConfig
(message)StreamingSynthesizeRequest
(message)StreamingSynthesizeResponse
(message)SynthesisInput
(message)SynthesizeLongAudioMetadata
(message)SynthesizeLongAudioRequest
(message)SynthesizeLongAudioResponse
(message)SynthesizeSpeechRequest
(message)SynthesizeSpeechRequest.TimepointType
(enum)SynthesizeSpeechResponse
(message)Timepoint
(message)Voice
(message)VoiceCloneParams
(message)VoiceSelectionParams
(message)
TextToSpeech
Service that implements Google Cloud Text-to-Speech API.
ListVoices |
---|
Returns a list of Voice supported for synthesis.
|
StreamingSynthesize |
---|
Performs bidirectional streaming speech synthesis: receive audio while sending text.
|
SynthesizeSpeech |
---|
Synthesizes speech synchronously: receive results after all text input has been processed.
|
TextToSpeechLongAudioSynthesize
Service that implements Google Cloud Text-to-Speech API.
SynthesizeLongAudio |
---|
Synthesizes long form text asynchronously.
|
AudioConfig
Description of audio data to be synthesized.
Fields | |
---|---|
audio_encoding |
Required. The format of the audio byte stream. |
speaking_rate |
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 |
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 |
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 |
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 |
effects_profile_id[] |
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 |
Required. The name of the AutoML model that synthesizes the custom voice. |
reported_usage |
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 |
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 |
ListVoicesResponse
The message returned to the client by the ListVoices
method.
Fields | |
---|---|
voices[] |
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
|
|
text |
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 |
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 to be used in this streaming attempt. Only specified in the first message sent in a |
input |
Input to synthesize. Specified in all messages but the first in a |
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 |
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 |
The raw text to be synthesized. |
ssml |
The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return |
SynthesizeLongAudioMetadata
Metadata for response returned by the SynthesizeLongAudio
method.
Fields | |
---|---|
start_time |
Time when the request was received. |
last_update_time |
Deprecated. Do not use. |
progress_percentage |
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 |
The resource states of the request in the form of |
input |
Required. The Synthesizer requires either plain text or SSML as input. |
audio_config |
Required. The configuration of the synthesized audio. |
output_gcs_uri |
Required. Specifies a Cloud Storage URI for the synthesis results. Must be specified in the format: |
voice |
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 |
Required. The Synthesizer requires either plain text or SSML as input. |
voice |
Required. The desired voice of the synthesized audio. |
audio_config |
Required. The configuration of the synthesized audio. |
enable_time_pointing[] |
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 |
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[] |
A link between a position in the original request input and a corresponding time in the output audio. It's only supported via |
audio_config |
The audio metadata of |
Timepoint
This contains a mapping between a certain point in the input text and a corresponding time in the output audio.
Fields | |
---|---|
mark_name |
Timepoint name as received from the client within |
time_seconds |
Time offset in seconds from the start of the synthesized audio. |
Voice
Description of a voice supported by the TTS service.
Fields | |
---|---|
language_codes[] |
The languages that this voice supports, expressed as BCP-47 language tags (e.g. "en-US", "es-419", "cmn-tw"). |
name |
The name of this voice. Each distinct voice has a unique name. |
ssml_gender |
The gender of this voice. |
natural_sample_rate_hertz |
The natural sample rate (in hertz) for this voice. |
VoiceCloneParams
The configuration of Voice Clone feature.
Fields | |
---|---|
voice_cloning_key |
Required. Created by GenerateVoiceCloningKey. |
VoiceSelectionParams
Description of which voice to use for a synthesis request.
Fields | |
---|---|
language_code |
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 |
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 |
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 |
The configuration for a custom voice. If [CustomVoiceParams.model] is set, the service will choose the custom voice matching the specified configuration. |
voice_clone |
The configuration for a voice clone. If [VoiceCloneParams.voice_clone_key] is set, the service will choose the voice clone matching the specified configuration. |