Upload an audio file, generate subtitles with Whisper, then review and export as SRT, VTT, or ASS. For video, use the Video to Subtitle tool.
Powered by OpenAI Whisper, this free online tool transcribes audio files into accurate, timestamped subtitles you can edit and export as SRT, VTT, or ASS.
Uses OpenAI's Whisper model to deliver accurate speech-to-text transcription across many languages and accents.
Upload MP3, WAV, M4A, AAC, FLAC, OGG, Opus, and more up to 100 MB. This page is for audio files only.
Let Whisper detect the spoken language, or manually select from 19 supported languages for more accurate results.
Edit cues in the preview, pick SubRip, WebVTT, or Advanced SubStation Alpha, then download a file ready for players or editors.
Drag and drop or click to select an audio file from your device. Supports MP3, WAV, M4A, AAC, FLAC, OGG, and more up to 100 MB.
Choose the spoken language or use auto-detect, then click Generate Subtitles. Whisper processes the audio and returns timed subtitles.
Check the subtitle preview, double-click any cue to correct errors, choose SRT, VTT, or ASS, then download.
Generate subtitles from audio when you have a podcast, voice memo, interview, lecture, or narration track and need timed captions for editing or publishing.
Create subtitles or transcripts from spoken audio before publishing clips.
Turn long-form spoken recordings into timed text for review and editing.
Generate SRT or VTT captions for voiceover tracks used in videos.
Clear speech and low background noise improve transcription accuracy.
Manual language selection can help when auto-detect guesses incorrectly.
Review cue text before downloading to catch names and specialized terms.
Download SRT for broad support, VTT for web, or ASS for styled workflows.