ComfyUI Node
deAPI Transcribe Audio
Transcribe speech to text with Whisper. Connect an AUDIO input, or paste a media URL (YouTube, X, Twitch, Kick, or a direct audio/video link).
deAPI Transcribe Audio
- audio
- text
◄modelWhisperLargeV3►
◄include_timestampsfalse►
◄source_url►
◄language►
◄api_key►
CategorydeAPI
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | WhisperLargeV3 | 2 options: WhisperLargeV3, WhisperLargeV3Ct2 |
| include_timestamps | BOOLEAN | false | — |
| audioopt | AUDIO | — | |
| source_urlopt | STRING | Used when no audio is connected. | |
| languageopt | STRING | Optional ISO code, e.g. en. Empty = auto-detect. | |
| api_keyopt | STRING | deAPI API key. Leave empty to use the DEAPI_API_KEY environment variable. A key typed here is saved in the workflow and in the metadata of every image ComfyUI saves. Get one at https://app.deapi.ai/register |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |