Cloud Text-to-Speech API . voices

Instance Methods

close()

Close httplib2 connections.

generateVoiceCloningKey(body=None, x__xgafv=None)

Generates voice clone key given a short voice prompt. This method validates the voice prompts with a series of checks against the voice talent statement to verify the voice clone is safe to generate.

list(languageCode=None, x__xgafv=None)

Returns a list of Voice supported for synthesis.

Method Details

close()
Close httplib2 connections.
generateVoiceCloningKey(body=None, x__xgafv=None)
Generates voice clone key given a short voice prompt. This method validates the voice prompts with a series of checks against the voice talent statement to verify the voice clone is safe to generate.

Args:
  body: object, The request body.
    The object takes the form of:

{ # Request message for the `GenerateVoiceCloningKey` method.
  "consentScript": "A String", # Required. The script used for the voice talent statement. The script will be provided to the caller through other channels. It must be returned unchanged in this field.
  "languageCode": "A String", # 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/languages) for a list of the currently supported language codes.
  "referenceAudio": { # Holds audio content and config. # Required. The training audio used to create voice clone. This is currently limited to LINEAR16 PCM WAV files mono audio with 24khz sample rate. This needs to be specified in [InputAudio.audio_config], other values will be explicitly rejected.
    "audioConfig": { # Description of inputted audio data. # Required. Provides information that specifies how to process content.
      "audioEncoding": "A String", # Required. The format of the audio byte stream.
      "sampleRateHertz": 42, # Required. The sample rate (in hertz) for this audio.
    },
    "content": "A String", # Required. The audio data bytes encoded as specified in `InputAudioConfig`. Note: as with all bytes fields, proto buffers use a pure binary representation, whereas JSON representations use base64. Audio samples should be between 5-25 seconds in length.
  },
  "voiceTalentConsent": { # Holds audio content and config. # Required. The voice talent audio used to verify consent to voice clone.
    "audioConfig": { # Description of inputted audio data. # Required. Provides information that specifies how to process content.
      "audioEncoding": "A String", # Required. The format of the audio byte stream.
      "sampleRateHertz": 42, # Required. The sample rate (in hertz) for this audio.
    },
    "content": "A String", # Required. The audio data bytes encoded as specified in `InputAudioConfig`. Note: as with all bytes fields, proto buffers use a pure binary representation, whereas JSON representations use base64. Audio samples should be between 5-25 seconds in length.
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for the `GenerateVoiceCloningKey` method.
  "voiceCloningKey": "A String", # The voice clone key. Use it in the SynthesizeSpeechRequest by setting [voice.voice_clone.voice_cloning_key].
}
list(languageCode=None, x__xgafv=None)
Returns a list of Voice supported for synthesis.

Args:
  languageCode: string, Optional. Recommended. [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) 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.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # The message returned to the client by the `ListVoices` method.
  "voices": [ # The list of voices.
    { # Description of a voice supported by the TTS service.
      "languageCodes": [ # The languages that this voice supports, expressed as [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g. "en-US", "es-419", "cmn-tw").
        "A String",
      ],
      "name": "A String", # The name of this voice. Each distinct voice has a unique name.
      "naturalSampleRateHertz": 42, # The natural sample rate (in hertz) for this voice.
      "ssmlGender": "A String", # The gender of this voice.
    },
  ],
}