Higgs TTS 3

Esta página de Soniqo documenta Higgs TTS 3 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	Higgs TTS 3
Rol	Conversational TTS and zero-shot cloning with inline emotion, style, and SFX tags
Backend	MLX bf16 backbone with float32 codec
Salida	24 kHz mono waveform, 25 frames per second
Idiomas	100+ languages
Licencia	Boson Higgs TTS 3 Research and Non-Commercial License
Estado	Ready through speech speak --engine higgs and the HiggsTTS Swift product
Fuente	Boson AI higgs-tts-3-4b
Producto Swift	`HiggsTTS`
CLI / runtime	`speech speak --engine higgs`

Uso

El fragmento siguiente refleja la API o el comando actual expuesto por speech-swift.

# Expressive cloned speech with an inline emotion tag.
.build/release/speech speak "<|emotion:elation|> We did it — the demo works!" \
  --engine higgs \
  --voice-sample reference.wav \
  --higgs-ref-text "Text spoken in the reference clip." \
  -o higgs.wav

Enlaces del modelo

Notas de implementación

RTF 0.78 on an M5 Pro for cloned and plain synthesis alike: sampling stays on the GPU with the delay ramp masked on-device, and asyncEval overlaps decode with the end-of-codes state machine.
Cloning gates: English lexical overlap 1.00 and Mandarin CER 0.000 on ASR roundtrips; the language model and codec are parity-validated against the upstream implementations in both directions.
Control tags are ordinary tokens inside the target text: <|emotion:...|>, <|style:whispering|>, <|sfx:laughter|>, <|prosody:pause|> and friends.
Encoding a 12 s reference costs about 0.6 s once and the codes are reusable across generations; omit --voice-sample for reference-free synthesis in a stock voice.
The CLI defaults to temperature 0.8 because the upstream 1.0 wobbles on single sentences; expect about 8.6 GB peak RSS for the 4B backbone.