Free Speech to Text
Speech to Text transcribes audio and video files, or a microphone recording, in about 100 languages with OpenAI's open-source Whisper model. The model, from 67 MB (Tiny) to 1.6 GB (Large v3 Turbo), is downloaded once and runs on your device. Turn on translation to English if needed, edit the transcript and export TXT, Word, SRT, VTT or JSON.
- Whisper models:
- Tiny, Base, Small, Large v3 Turbo
- Export:
- TXT, Word, SRT, VTT, JSON
- Languages:
- About 100; translate to English
- Price:
- Free
- Runs:
- AI model in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Is my recording uploaded?
No. The Whisper model is downloaded once from Hugging Face and runs in your browser; the audio never leaves your device.
Which languages are supported?
About 100 languages, from English, Spanish and Chinese to Welsh and Swahili. Accuracy is highest for widely spoken languages and with the larger models.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Speech to Text
- Drop an audio or video file, or record from the microphone.
- Pick a model (Tiny is fastest, Small and Large v3 Turbo are the most accurate) and the language, or let it detect the language.
- Click Transcribe: the text appears as it is recognized; Cancel keeps what is done.
- Search, click a sentence to hear it, fix words in Edit mode, then export TXT, Word, SRT, VTT or JSON.
Credits & open source
Open-source AI model running in your browser. Thank you to the people who make these projects.
- Transformers.jsRuns Hugging Face AI models in the browser with ONNX Runtime. © Hugging Face, Inc. and contributors · Apache-2.0
- ONNX Runtime WebExecutes ONNX models with WebGPU or WebAssembly (self-hosted from /vendor/ort). © Microsoft Corporation · MIT
- MediabunnyReads, writes and converts media files with WebCodecs (MP4, WebM, MKV, MOV, MP3, WAV, Ogg...). © Vanilagy and contributors · MPL-2.0
- docxCreates Word .docx files. © Dolan Miu · MIT
Web platform APIs used: Web Workers, WebAssembly, WebCodecs, Web Audio API, Media Capture (getUserMedia), MediaRecorder, File API, localStorage.
- Whisper tiny / base / small (ONNX, timestamped exports) by OpenAI (model); onnx-community (ONNX conversion) (MIT (openai/whisper; the Hugging Face model cards list Apache-2.0)) — speech recognition and translation to English with word timestamps
- Whisper large-v3-turbo (ONNX, timestamped export) by OpenAI (model); onnx-community (ONNX conversion) (MIT) — most accurate option, WebGPU only
Full license texts: third-party notices · all credits
Frequently asked questions
Can it translate?
Yes: turn on Translate to English to get English text from speech in any supported language (not available with Large v3 Turbo).
How long can the file be?
Hours, if your device has enough memory: audio is processed in 30-second windows. One hour of audio takes about 230 MB of memory; WebGPU makes it several times faster.
Can I get subtitles?
Export SRT or VTT here, or use the Subtitle Generator to edit cues, style them and burn them into the video.