Audio → Text · AI

Transcribe audio to text, in your browser.

Drop an audio or video file and get a transcript plus ready-to-use .srt / .vtt subtitles — powered by on-device AI (Whisper). No sign-up.

Your audio stays on your device. The AI model downloads once and is cached.
Drop your audio or video here
or click to choose a file · common audio or video your browser can decode (MP3, M4A, WAV, OGG, FLAC, MP4…) · stays on your device
—
0:00 / 0:00
Preparing…

Transcript

First run downloads the Whisper model (one-time, then cached). Transcription runs on your device — longer clips take longer, especially on older phones.

How to transcribe audio to text

  1. Drop your file in. Choose or drag a common audio or video file your browser can decode — it's decoded locally and never uploaded.
  2. Transcribe. The first run downloads the AI model once (then it's cached); transcription runs entirely on your device.
  3. Copy or export. Grab the text, or download a .txt transcript or .srt/.vtt subtitles.

Frequently asked questions (5)
Is it free?

Yes — completely free, with no sign-up and no per-minute charges.

Is my audio uploaded anywhere?

No. Your audio is transcribed locally in your browser and never leaves your device. Only the AI model is downloaded once (from TrackMix's own servers) and then cached.

Why is the first run slow?

The first transcription downloads the Whisper model (a one-time download). After that it's cached, and only the transcription time remains — which depends on clip length and your device.

What languages does it handle?

Whisper is multilingual and auto-detects the language; accuracy is best on clear speech.

Can I get subtitles?

Yes — export timed .srt or .vtt subtitle files alongside the plain-text transcript.

Related tools

Voice RecorderRecord from mic Noise ReducerReduce background noise Silence RemoverCut dead air Audio CutterCut & trim audio NormalizerEven out loudness