OmniVoice
Esta página da Soniqo documenta OmniVoice conforme a implementação local em speech-swift / speech-core. Os links do Hugging Face ficam abaixo das notas de integração.
Página interna primeiro
Cards e menus apontam primeiro para cá; os links do modelo fonte e dos bundles continuam disponíveis nesta página.
Visão geral
| Modelo | OmniVoice |
|---|---|
| Papel | Massively multilingual zero-shot voice-cloning TTS |
| Backend | MLX int8 default bundle; fp16 bundle available |
| Saída | 24 kHz mono waveform |
| Idiomas | 600+ languages |
| Licença | Apache-2.0 upstream family |
| Status | Programmatic speech-swift runtime used by Studio sidecar |
| Fonte | k2-fsa OmniVoice |
| Produto Swift | OmniVoiceTTS |
| CLI / runtime | Programmatic runtime; not a primary speech speak engine yet |
Uso
O trecho abaixo reflete a API ou comando atual exposto 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"
)Links do modelo
Notas de implementação
- 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.