ComfyUI Node
Generate Speech [BETA] (Venice)
A ComfyUI node in venice.ai with 5 inputs and 1 output.
Generate Speech [BETA] (Venice)
- audio
◄modeltts-kokoro►
◄input►
◄response_formatmp3►
◄speed1.00►
◄voiceaf_sky - tts-kokoro►
Categoryvenice.ai
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | tts-kokoro | — |
| input | STRING | The text to generate audio for. The maximum length is 4096 characters. | |
| response_format | COMBO | mp3 | mp3: widely supported, lossy; wav: lossless raw audio; pcm: uncompressed raw audio. |
| speed | FLOAT | 1.000.25–4 | The text to image style to apply during prompt enhancement. Does best with short descriptive prompts, like gold, marble or angry, menacing. |
| voice | COMBO | af_sky - tts-kokoro | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |