All tools

aiquick/transcribe

audio-to-text

Speech recognition on the audio inference worker. Upload a clip and get the transcript back, with per-segment timings when the model provides them.

Inference/audio/transcribe

Input

Audio file *Up to 25 MB. WAV, MP3, M4A, FLAC, or OGG.
LanguageOptional ISO code, e.g. en. Leave blank to let the model detect it.

Result

Idle
Fill in the input and run the tool to see results here.