ComfyUI Node Runs on cloud
ElevenLabs Text to Dialogue
Generate multi-speaker dialogue from text. Each dialogue entry has its own text and voice.
ElevenLabs Text to Dialogue
- AUDIO
◄stability0.5►
◄apply_text_normalization▾►
◄model▾►
◄inputs▾►
◄language_code►
◄seed1►
◄output_format▾►
Categorypartner/audio/ElevenLabs
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| stability | FLOAT | 0.50–1 | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech. |
| apply_text_normalization | COMBO | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. | |
| model | COMBO | Model to use for dialogue generation. | |
| inputs | COMBO | Number of dialogue entries. | |
| language_code | STRING | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection. | |
| seed | INT | 10–4294967295 | Seed for reproducibility. |
| output_format | COMBO | Audio output format. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| AUDIO | AUDIO | — |