Higgs TTS 3
이 Soniqo 페이지는 로컬 speech-swift / speech-core 구현의 Higgs TTS 3을 설명합니다. Hugging Face 번들 링크는 통합 메모 뒤에 있습니다.
내부 페이지 우선
랜딩 카드와 문서 메뉴는 먼저 이 페이지로 이동하고, 원본 모델과 번들 링크는 이 페이지 안에 둡니다.
개요
| 모델 | Higgs TTS 3 |
|---|---|
| 역할 | Conversational TTS and zero-shot cloning with inline emotion, style, and SFX tags |
| 백엔드 | MLX bf16 backbone with float32 codec |
| 출력 | 24 kHz mono waveform, 25 frames per second |
| 언어 | 100+ languages |
| 라이선스 | Boson Higgs TTS 3 Research and Non-Commercial License |
| 상태 | Ready through speech speak --engine higgs and the HiggsTTS Swift product |
| 소스 | Boson AI higgs-tts-3-4b |
| Swift 제품 | HiggsTTS |
| CLI / 런타임 | speech speak --engine higgs |
사용
아래 스니펫은 현재 speech-swift 저장소의 API 또는 명령과 일치합니다.
# 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.wav모델 링크
구현 메모
- 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.