Audio Transcription

Workspace Tools · Browser tool · Audio & Video

Drop an audio file or click to upload

MP3, M4A, WAV, OGG, or FLAC — max 5 min on your plan

TimestampsSpeaker labelsSpoken language (optional)

Your audio is processed by the AI model for transcription and deleted right away — it is not stored.

Transcription uses 1 AI request per started 10 minutes of audio.

Learn more about this tool

What is Audio Transcription?

Audio Transcription converts MP3, M4A, WAV, OGG, or FLAC audio into editable text. It can include timestamps, speaker labels, and an optional language hint.

The result can be copied, downloaded as a TXT file, or downloaded as an SRT subtitle file when timestamps are enabled.

Who Is This Tool For?

Teams converting interviews, meetings, lectures, or voice notes into text.
Video creators preparing timestamped subtitle files.
Students and researchers reviewing spoken material in a searchable format.

Common Use Cases

Create a transcript from a recorded interview with optional speaker labels.
Download timestamped captions as an SRT file for a video editor.
Turn a lecture or voice memo into text for notes and search.

How to Transcribe Audio

Drop or upload a supported audio file within the size and duration limit shown for your plan.
Choose whether to include timestamps and speaker labels, and optionally enter a language hint.
Start transcription and wait for the detected segments to appear.
Copy the transcript or download TXT; download SRT when timestamps were enabled.

The audio file is uploaded for AI transcription. Account and quota limits apply, and processing follows the published Privacy Policy.