Skip to content

Audio transcription

Turn audio or video (up to 60 min) into text with timestamps. The audio is prepared in your browser and sent to the speech provider.

AvailableExternal APIInput: Audio

How to use: Audio transcription

  1. Choose an audio or video file (up to 60 minutes).
  2. Set the spoken language or leave “Detect language”.
  3. Wait: the audio is prepared in your browser first, then transcribed.
  4. Copy or download the transcript, with or without timestamps.

What it accepts and what you get

Input
Audio up to 100 MB or video up to 200 MB and 60 minutes that your browser can decode.
Output
Text with [mm:ss] timestamps per segment, to copy or download as .txt.
Where your data is processed
The audio is converted to mono MP3 in your browser and only that audio (never the video) is sent to the speech provider. TodoToolsOnline does not store or log the audio, but the provider handles it under its own policy. Do not include confidential data.

Limitations and notes

  • The audio is converted to mono MP3 (32 kbps) in your browser and only that audio —never the video— is sent to the speech provider.
  • Quality depends on the audio, the language and the model; proper names and technical terms can be wrong.
  • The provider may have free-tier usage limits per hour.
  • TodoToolsOnline does not store or log the content; the AI provider handles it under its own policy: do not include confidential data.
  • AI can make mistakes: always check the result.
  • There are per-minute and daily usage limits to prevent abuse.
  • If the administrator has not switched the provider on, the tool says so and processes nothing.