Speech to text.
Transcribe a recording, voice note, meeting or video into text, or record straight from your microphone. The transcribing happens in your browser, so your audio stays with you.
More tools
See all tools
Summarise PDFGet the key points of a PDF, Word file or text with on-device AI.
Translate DocumentTranslate a PDF or Word file into 27 languages on your device.
AI Image UpscalerEnlarge a photo 2× or 4× with sharper detail, on your device.
Background RemoverRemove a photo’s background with on-device AI.Speech to text: quick facts
Transcribe audio or video into text or subtitles with AI on your device.
Updated
- Price
- Free. No sign-up, no watermark.
- Input
- MP3, WAV, M4A, OGG, WebM, FLAC, and the sound from MP4 or MOV videos.
- Output
- Text, timestamps or .srt subtitles; optional English translation.
- AI model
- About 40 MB (Fast) or 80 to 150 MB (More accurate), downloaded once.
- Speed
- A one-hour recording often takes a few minutes on a modern computer.
- Privacy
- Your recording is transcribed in your browser and never uploaded.
How to transcribe a recording to text
Add an audio or video file, or record from your microphone, choose Fast or More accurate, and transcribe. Copy the text, download it as .txt, or save subtitles as an .srt file.
- 01
Add a recording
Upload audio or video, or record from your microphone.
- 02
Transcribe
Choose the language (or let it detect it) and press Transcribe.
- 03
Download
Save the transcript as text, or as .srt subtitles for a video.
Tips for a more accurate transcript
The recording itself decides most of the accuracy, so a little care before you press record pays off.
- Record clear audioTranscription is most accurate when one person speaks at a time, close to the microphone, without music or traffic behind them. A little care while recording saves a lot of correcting afterwards.
- Use More accurate for anything importantFast is fine for a quick voice note. For interviews, lectures or anything you’ll quote, choose More accurate: it downloads a larger model once and takes longer, but makes fewer mistakes with names and technical words.
- Set the language if it guesses wrongIf the language is detected wrongly, choose it under Spoken language. To get English from speech in another language, set Output to English translation instead.
- Add subtitles to your videosDownload subtitles (.srt) saves timed captions you can add to a video on YouTube, in most video editors, and in players such as VLC.
Like every Altto tool, this runs on your device — nothing you add is uploaded. How Altto works
of recording often takes just a few minutes to transcribe on a modern computer with a recent browser. Older or less powerful devices take longer.
Will it run on my device?
Because the AI runs on your own device instead of on a server, your computer does the work — that’s what keeps your files private. Most computers from the last few years are fine, but a more powerful one is noticeably faster.
Minimum
- ComputerAny laptop or desktop from about the last 6 years
- Memory (RAM)4 GB
- BrowserThe latest Chrome, Edge, Firefox or Safari
- QualityUse “Fast” (about 40 MB download)
Without graphics acceleration, a recording can take as long to transcribe as it does to play.
Recommended Fastest
- ComputerA recent laptop or desktop (e.g. Intel Core i5 / AMD Ryzen 5 or better)
- Memory (RAM)8 GB or more
- BrowserChrome or Edge, which can use your graphics chip (WebGPU)
- Quality“More accurate” (about 80–150 MB download)
Phones can transcribe short voice notes; for long recordings use a computer.
Tested on a mid-range PC with AMD Ryzen built-in graphics (no separate graphics card), in Chrome: An 11-second clip transcribed in about 3 seconds once the model was downloaded (roughly 20 minutes for an hour-long recording on the same PC).