Transcribe audio with a specific Hub model
One step with Hugging Face. We can help you get access.
Get something done
Transcribe audio with a specific Hub model
with Hugging Face · Speech & Voice
Use Hugging Face: its Hugging Face Audio API lets you transcribe audio with a specific Hub model in a single step (POST /models/{model_id}/automatic-speech-recognition). capabilities.work can help you get signed up and connected.
- Can I send an audio clip straight to a particular speech recognition model on the Hub and get text back?
- Which serverless inference route runs a chosen ASR model like Whisper by its model ID?
Say it to your AI assistant
- Transcribe this recording using the speech recognition model {model_id}.
- Run automatic speech recognition inference on model {model_id} for my audio clip.
For your developer
POST /models/{model_id}/automatic-speech-recognition in Hugging Face Audio API. Full spec on APIs.io.