Transcribe English audio to text
Turn English audio or video into text with AI speech recognition that runs on your device — no upload, no account. Export as TXT or SRT subtitles.
How to audio to text
- Select or drop an English audio or video file.
- Click “Transcribe” — the AI model loads once, then runs on your device.
- Wait while it converts speech to text.
- Copy the transcript or download it as .txt or .srt subtitles.
No file uploads
Free & unlimited
No watermark
Frequently asked questions
Is my audio uploaded to a server?
No. The speech-recognition model (OpenAI Whisper) downloads once and runs entirely in your browser, so your recording never leaves your device.
What languages does it support?
This tool transcribes English audio only. It uses a fast, on-device English speech model, so clear English recordings transcribe best. Other languages are not supported.
Can I get subtitles?
Yes. Download the result as an .srt subtitle file with timestamps, or as plain .txt.
Why is the first run slow?
The AI model (~tens of MB) is downloaded the first time, then cached. Transcription runs roughly in real time, so longer files take longer.