Audio to Text

Transcribe speech or audio into text (speech-to-text integration coming soon)

Select Audio *

Formats: MP3, WAV, M4A, AAC, FLAC, OGG, WEBM (short clips recommended)

Language

Options

Generate timestamps (SRT/VTT)

Attempt speaker diarization

Preserve punctuation

Max segment length

This tool needs a speech-to-text backend (e.g., OpenAI Whisper, Azure Speech). For now, you can use the UI and exports with any returned transcript.

Upload an audio file and click Transcribe

Export TXT, SRT, and VTT once a transcript is returned