OmniVoice
Esta página de Soniqo documenta OmniVoice tal como está implementado en speech-swift / speech-core. Los enlaces a Hugging Face aparecen debajo de las notas de integración.
Primero página interna
Las tarjetas y menús apuntan primero aquí; los enlaces al modelo fuente y a los bundles siguen disponibles en esta página.
Resumen
| Modelo | OmniVoice |
|---|---|
| Rol | Massively multilingual zero-shot voice-cloning TTS |
| Backend | MLX int8 default bundle; fp16 bundle available |
| Salida | 24 kHz mono waveform |
| Idiomas | 600+ languages |
| Licencia | Apache-2.0 upstream family |
| Estado | Programmatic speech-swift runtime used by Studio sidecar |
| Fuente | k2-fsa OmniVoice |
| Producto Swift | OmniVoiceTTS |
| CLI / runtime | Programmatic runtime; not a primary speech speak engine yet |
Uso
El fragmento siguiente refleja la API o el comando actual expuesto por speech-swift.
import OmniVoiceTTS
let model = try await OmniVoiceTTSModel.fromPretrained()
let pcm = try model.generate(
text: "A new sentence in the reference speaker's voice.",
referenceAudio: URL(fileURLWithPath: "reference.wav"),
referenceText: "This is the reference voice.",
language: "en"
)Enlaces del modelo
Notas de implementación
- Download repairs incomplete caches by checking the backbone, tokenizer files, and audio_tokenizer model before loading.
- Generation iteratively unmasks eight acoustic codebooks with classifier-free guidance.
- The runtime combines a bidirectional Qwen3 backbone with a Higgs-audio v2 codec encoder/decoder.
- Optional instructions cover restricted style controls such as accent, age, gender, pitch, and whisper.