ComfyUI Node
Whisper 1 语音转写
A ComfyUI node in Seedance with 6 inputs and 2 outputs.
Whisper 1 语音转写
- audio
- api_config
- text
- response
◄modelwhisper-1►
◄response_formatjson►
◄skip_errorfalse►
◄seed0►
CategorySeedance
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | Input audio to transcribe; converted to wav before upload. | 需要转写的音频，会先转换为 wav 再上传。 | |
| model | COMBO | whisper-1 | Whisper transcription model. | Whisper 语音转写模型。 |
| response_format | COMBO | json | API response format: json, verbose_json, srt, text, or vtt. | API 返回格式。 |
| api_configopt | SEEDANCE_CONFIG | Connect Seedance API Config; otherwise SEEDANCE_API_KEY is used. | |
| skip_erroropt | BOOLEAN | false | On failure return an empty transcript and JSON error instead of stopping the workflow. | 失败时返回空文本和错误 JSON。 |
| seedopt | INT | 00–18446744073709550000 | ComfyUI cache seed. Fixed reuses the cached result while all other inputs stay unchanged; randomize/increment/decrement starts a new execution. This value is not sent to models without documented seed support. | ComfyUI 缓存种子；Fixed 在其他输入不变时复用缓存，随机、递增或递减会触发新任务。未声明支持 seed 的模型不会收到此参数。 |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| response | STRING | — |