ComfyUI Node Runs on cloud
ElevenLabs Speech to Text
Transcribe audio to text. Supports automatic language detection, speaker diarization, and audio event tagging.
ElevenLabs Speech to Text
- audio
- text
- language_code
- words_json
◄model▾►
◄language_code►
◄num_speakers0►
◄seed1►
Categorypartner/audio/ElevenLabs
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | Audio to transcribe. | |
| model | COMBO | Model to use for transcription. | |
| language_code | STRING | ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection. | |
| num_speakers | INT | 00–32 | Maximum number of speakers to predict. Set to 0 for automatic detection. |
| seed | INT | 10–2147483647 | Seed for reproducibility (determinism not guaranteed). |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| language_code | STRING | — |
| words_json | STRING | — |