Transcribe an uploaded audio file
One step with Hugging Face. We can help you get access.
Get something done
Transcribe an uploaded audio file
with Hugging Face · Speech & Voice
Use Hugging Face: its Hugging Face Audio API lets you transcribe an uploaded audio file in a single step (POST /v1/audio/transcriptions). capabilities.work can help you get signed up and connected.
- Is there an audio transcriptions endpoint where I upload a file and pick the model?
- Can I tell the transcriber what language the audio is in and give it a guiding prompt?
- What output formats can a file transcription come back in, like plain text or JSON?
Say it to your AI assistant
- Upload {file} and transcribe it with model {model}.
- Transcribe audio file {file} with {model}, treating the spoken language as {language}.
- Transcribe {file} using {model} and hint the vocabulary with the prompt {prompt}.
For your developer
POST /v1/audio/transcriptions in Hugging Face Audio API. Full spec on APIs.io.