TTS

pydantic model TTS

Bases: BaseTTS

Multilingual text-to-speech using the Google TTS API

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Config:

• arbitrary_types_allowed: bool = True

Fields:

• audio_config (google.cloud.texttospeech_v1.types.cloud_tts.AudioConfig | None)

• client (google.cloud.texttospeech_v1.services.text_to_speech.client.TextToSpeechClient | None)

• language (str)

• voice_gender (int)

field audio_config: AudioConfig | None = None

Audio config for return encoding type (MP3)

field client: TextToSpeechClient | None = None

Google TTS client

field language: str [Required]

TTS input language name [see Supported Languages]

field voice_gender: int = SsmlVoiceGender.NEUTRAL

TTS voice gender

run(tts_input: str) → None

Convert tts to audio and output to speaker

property voice: VoiceSelectionParams

Select TTS voice from language and gender