Skip to main content

Voice Management

Preset Voices​

list_preset_voices()​

voices = tts.list_preset_voices()
# Returns: List[tuple[str, str]]  →  [(description, voice_id), ...]

get_preset_voice()​

voice = tts.get_preset_voice(voice_name: str = None)
# Returns: dict  →  {"codes": Tensor, "text": str}

Using a Preset Voice​

voices = tts.list_preset_voices()
voice = tts.get_preset_voice("bac_si_tuyen")
audio = tts.infer(text="Chào bạn!", voice=voice)

LoRA Adapters​

load_lora_adapter()​

success = tts.load_lora_adapter(
    lora_repo_id: str,
    hf_token: str = None,
)

unload_lora_adapter()​

success = tts.unload_lora_adapter()

voices.json Format​

{
  "default_voice": "voice_name",
  "presets": {
    "voice_name": {
      "description": "Description of the voice",
      "text": "Transcript of the reference audio",
      "codes": [42, 17, 89, 55, ...]
    }
  }
}