ComfyUI Node
Ollama Audio Transcribe
Transcribe audio to text using an Ollama speech-to-text model such as whisper.
Ollama Audio Transcribe
- audio
- text
◄urlhttp://127.0.0.1:11434►
◄model▾►
◄prompt►
◄language►
◄temperature0.00►
CategoryOllama/Audio
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | Audio to transcribe. Connect from Load Audio or any AUDIO output. | |
| url | STRING | http://127.0.0.1:11434 | URL of the Ollama server. |
| model | COMBO | Speech-to-text model (e.g. whisper, whisper-large-v3-turbo). | |
| promptopt | STRING | Optional hint to guide transcription (vocabulary hints, speaker style, etc.). | |
| languageopt | STRING | BCP-47 language code (e.g. 'en', 'fr', 'ja'). Leave blank for auto-detect. | |
| temperatureopt | FLOAT | 0.000–1 | Sampling temperature. 0 = deterministic. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |