Higgs TTS 3
यह Soniqo पेज स्थानीय speech-swift / speech-core implementation में Higgs TTS 3 को दस्तावेज़ करता है। Hugging Face bundle links integration notes के बाद दिए गए हैं।
पहले आंतरिक पेज
Landing cards और docs menus पहले इसी पेज पर आते हैं; source model और bundle links यहीं उपलब्ध रहते हैं।
सारांश
| मॉडल | Higgs TTS 3 |
|---|---|
| भूमिका | Conversational TTS and zero-shot cloning with inline emotion, style, and SFX tags |
| Backend | MLX bf16 backbone with float32 codec |
| Output | 24 kHz mono waveform, 25 frames per second |
| भाषाएँ | 100+ languages |
| लाइसेंस | Boson Higgs TTS 3 Research and Non-Commercial License |
| स्थिति | Ready through speech speak --engine higgs and the HiggsTTS Swift product |
| Source | Boson AI higgs-tts-3-4b |
| Swift product | HiggsTTS |
| CLI / runtime | speech speak --engine higgs |
उपयोग
नीचे का snippet मौजूदा speech-swift API या command से मेल खाता है।
# 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.wavमॉडल लिंक
implementation notes
- 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.