Free Offline English Speech to Text
VoiceScriber's free browser tool converts English audio into timestamped text on your device. Upload a file or record up to 60 minutes, then copy the transcript or export TXT, timestamped TXT, JSON, or SRT. No account or audio upload is required.
Choose your audio source
MP3, WAV, M4A, AAC, OGG, FLAC
Updated June 11, 2026
What is this offline speech-to-text tool?
This is a free English transcription tool that runs speech recognition in your desktop browser. Your audio is processed on your device instead of being uploaded to a transcription server. The speech model downloads on first use and is cached by supported browsers for future sessions.
| Language | English. The VoiceScriber iPhone app supports 100+ languages. |
|---|---|
| Audio limit | Up to 60 minutes per uploaded file or microphone recording. |
| Audio formats | MP3, WAV, M4A, AAC, OGG and FLAC. Codec support can vary by browser. |
| Exports | TXT, timestamped TXT, JSON and SRT. |
| Privacy | Audio is processed on your device and is not uploaded to VoiceScriber. |
| Best experience | Designed for modern desktop browsers. For mobile, use the VoiceScriber iPhone app. |
How to transcribe audio in your browser
- Choose File or Microphone. Upload an audio file or record directly in the browser.
- Prepare up to 60 minutes of audio. The Transcribe button becomes available when a file or recording is ready.
- Transcribe and export. Copy the timestamped result or download it as TXT, timestamped TXT, JSON or SRT.
Frequently asked questions
Does this tool upload my audio?
No. The speech model is downloaded to your browser, and transcription runs on your device. Your uploaded file or microphone recording is not sent to VoiceScriber for processing.
Do I need an internet connection?
An internet connection is required to load the page and download the speech model on first use. Once the page and model are loaded, the transcription process itself runs locally without uploading your audio.
What audio file formats can I use?
The tool accepts common audio formats including MP3, WAV, M4A, AAC, OGG and FLAC. Actual codec support depends on your browser and operating system.
What is the maximum audio duration?
Uploaded files and microphone recordings are limited to 60 minutes. If an uploaded file is longer, only the first 60 minutes are prepared for transcription.
Which languages are supported?
This browser tool currently supports English only. For offline transcription in 100+ languages, download VoiceScriber for iPhone.
Can I use this speech-to-text tool on mobile?
The browser tool is designed to work best on desktop computers. For recording and transcription on iPhone, use the VoiceScriber mobile app.