Nodes/Higgs v3 TTS/Higgs v3 Multi-Speaker
ComfyUI Node

Higgs v3 Multi-Speaker

Generate dialogue with multiple cloned Higgs v3 voices using [Speaker_N]: tags.

By Saganaki22·Created 2 months ago·Updated 2 months ago· 64
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)

NameTypeDefaultDescription
higgs_modelHIGGSV3TTS_MODEL
textSTRING[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_speakersCOMBONumber of active speakers (2-6). Changing this adds or removes speaker audio/reference text inputs.
pause_between_speakersFLOAT0.300–3Seconds of silence inserted when moving from one speaker turn to the next.
max_new_tokensINT204832–8192Maximum audio-code tokens per single pass. 2048 is roughly 25-30 seconds; raise it or enable chunking if speech cuts off.
temperatureFLOAT1.000–2Sampling variety. 0 is greedy; around 0.8-1.1 is usually natural.
top_pFLOAT0.950–1Nucleus sampling cutoff. 1.0 disables it; 0.9-0.98 keeps speech expressive.
top_kINT500–1026Limits each codebook sample to the top K choices. 0 disables it.
seedINT00–21474836470 uses the current random state. A positive value is repeatable and is reused unchanged for every longform chunk.
longform_chunkingBOOLEANtrueSplit long text at sentence or pause-tag boundaries. Off is one direct pass and may stop early on long text.
words_per_chunkINT4520–300Target words per chunk. Around 35-55 fits the 2048-token default better; raise with max_new_tokens for longer chunks.
pause_between_chunksFLOAT0.150–2Seconds of silence inserted between longform chunks. Does not replace inline pause tags.

Outputs (1)

NameTypeDescription
audioAUDIO