ComfyUI Node
Higgs v3 Multi-Speaker
Generate dialogue with multiple cloned Higgs v3 voices using [Speaker_N]: tags.
Higgs v3 Multi-Speaker
- higgs_model
- audio
◄text[Speaker_1]: Hello, I am speaker one.
[Speaker_2]: And I am speaker two. <|sfx:laughter|>Haha, nice to meet you.►
◄num_speakers▾►
◄pause_between_speakers0.30►
◄max_new_tokens2048►
◄temperature1.00►
◄top_p0.95►
◄top_k50►
◄seed0►
◄longform_chunkingtrue►
◄words_per_chunk45►
◄pause_between_chunks0.15►
CategoryHiggs v3 TTS
Inputs (12)
| Name | Type | Default | Description |
|---|---|---|---|
| higgs_model | HIGGSV3TTS_MODEL | — | |
| text | STRING | [Speaker_1]: Hello, I am speaker one. [Speaker_2]: And I am speaker two. <|sfx:laughter|>Haha, nice to meet you. | Dialogue script. Use [Speaker_1]:, [Speaker_2]:, etc. Lines without a speaker tag continue the previous speaker. |
| num_speakers | COMBO | Number of active speakers (2-6). Changing this adds or removes speaker audio/reference text inputs. | |
| pause_between_speakers | FLOAT | 0.300–3 | Seconds of silence inserted when moving from one speaker turn to the next. |
| max_new_tokens | INT | 204832–8192 | Maximum audio-code tokens per single pass. 2048 is roughly 25-30 seconds; raise it or enable chunking if speech cuts off. |
| temperature | FLOAT | 1.000–2 | Sampling variety. 0 is greedy; around 0.8-1.1 is usually natural. |
| top_p | FLOAT | 0.950–1 | Nucleus sampling cutoff. 1.0 disables it; 0.9-0.98 keeps speech expressive. |
| top_k | INT | 500–1026 | Limits each codebook sample to the top K choices. 0 disables it. |
| seed | INT | 00–2147483647 | 0 uses the current random state. A positive value is repeatable and is reused unchanged for every longform chunk. |
| longform_chunking | BOOLEAN | true | Split long text at sentence or pause-tag boundaries. Off is one direct pass and may stop early on long text. |
| words_per_chunk | INT | 4520–300 | Target words per chunk. Around 35-55 fits the 2048-token default better; raise with max_new_tokens for longer chunks. |
| pause_between_chunks | FLOAT | 0.150–2 | Seconds of silence inserted between longform chunks. Does not replace inline pause tags. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |