Speech to Text
Transcribe voice notes, meetings and videos with OpenAI Whisper running on your device. Export TXT or SRT subtitles.
No uploads
How to use Speech to Text
- 1Open Speech to Text. It runs in your browser, no sign-up.
- 2Drop your file here or choose it. It stays on your device; nothing is uploaded.
- 3Adjust the options until the preview looks right.
- 4Download the result.
Questions
Is my recording uploaded?
No. OpenAI’s Whisper model runs in your browser via WebAssembly/WebGPU. Only the model downloads once.
Which languages?
Whisper understands ~100 languages and detects the language automatically.
How long can the audio be?
Any length, but browsers are slower than servers — expect about 1–3× real time with the Base model on a laptop.
More tools
Video to GIFClip, trim, loop Video CompressorShrink MP4 for sharing Audio Converter & CutterMP3, WAV, M4A, ringtones Video TrimmerCut clips without quality loss Video MergerJoin clips into one video Video Timeline EditorTrim, arrange, crossfade Mute Video & Extract AudioRemove sound or save it as MP3 Rotate & Flip VideoFix sideways phone videos