ComfyUI Node
Grok STT · Speech to Text
Transcripts with word timings in 25 languages 0.01 credits ($0.0001) per second. Model: xai/grok-stt/speech-to-text Fields, prices and examples: https://popnow.ai/docs/models/grok-stt
Grok STT · Speech to Text
- audio_url
- text
- task id
◄languagemodel default►
◄text_normalizationfalse►
◄keyterms►
◄filler_wordsfalse►
◄multichannelfalse►
CategoryPopNow/Audio/xAI
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| audio_url | AUDIO | Audio to transcribe: an uploaded MP3 or WAV, or a public URL to a common audio or video format. 1 second to 2 hours. | |
| language | COMBO | model default | Spoken language. Leave empty to detect it; required when text_normalization is on. |
| text_normalization | BOOLEAN | false | Write spoken numbers, prices, dates and units in digits. Needs language. |
| keyterms | STRING | Names and terms to spell the way you list them, up to 100. JSON. A list of objects with "term". | |
| filler_words | BOOLEAN | false | Keep filler words such as um and uh in the transcript. |
| multichannel | BOOLEAN | false | Transcribe each channel separately, one line per channel. Turn on when speakers are on separate channels. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |
| task id | STRING | The PopNow task id, for the API console logs or support. |