Audio transcription

Convert audio to editable text.

Upload an interview, meeting, voice note, lecture, or podcast and turn its speech into a transcript you can review, search, and export.

MP3, WAV, M4A, MPEG and WebM audioEditable transcriptTXT + subtitle export
Start for free

Turn a recording into usable text

No account required for your first transcription.

Drop audio or video hereor choose a file from your deviceMP3, WAV, M4A, MP4, MPEG, WebM · up to 100 MB

Files are stored privately while they are processed.

From upload to useful output

Everything needed for the next step.

01

Review with less friction

Edit the transcript directly on the result page before copying or saving it.

02

Export for your workflow

Download plain text, SRT, VTT, or CSV without reformatting the transcript by hand.

03

Return when you need it

Recent files stay linked to this browser so you can reopen their result pages.

How to use this tool

A straightforward path from recording to transcript.

Upload an interview, meeting, voice note, lecture, or podcast and turn its speech into a transcript you can review, search, and export. Voysum keeps the original upload workflow separate from the editable result, so you can follow progress and return to recent jobs from the same browser.

  1. 1

    Prepare a speech recording

    Choose an audio file with audible speech. A close microphone and limited music or background noise usually produce a transcript that needs fewer corrections.

  2. 2

    Choose the spoken language

    Select the language when you know it, or leave automatic detection enabled for recordings whose language is uncertain.

  3. 3

    Review words and timing

    Correct names or specialist terms in the editor, then export readable TXT or timestamped SRT, VTT, and CSV files.

Example output

What an audio transcript looks like

A meeting recording becomes editable text while its timing remains available for subtitle exports.

Recording segment00:00:04 We will publish the first version on Friday.Editable transcript
We will publish the first version on Friday.

TXT keeps the readable sentence. SRT and VTT keep the start and end times for captions.

Choose the right path

Audio transcription by source and format.

Start with the broad audio-to-text workflow, or open the page that matches the recording you already have. Each route leads to the same editable result and timed exports.

  1. MP3

    Transcribe an MP3 recording

    For podcasts, interviews, exported voice recordings, and compressed speech.

  2. WAV

    Transcribe WAV audio

    For lossless recorder files, meetings, research interviews, and production audio.

  3. M4A

    Transcribe an M4A voice memo

    For iPhone voice memos and recordings saved by mobile or meeting apps.

Worked example

See a recording become a usable interview transcript.

Our worked example shows the input, corrections, paragraph structure, timestamps, and export choices instead of describing the workflow in the abstract.

Read the complete example →

Original recording12-minute two-person product interview · M4AUseful output
Readable paragraphs, corrected names, timestamped quotes, and SRT captions.

The guide also explains what still needs human review and which audio problems affect accuracy.

Common questions

Audio transcription FAQ

Practical details about uploading, processing, and exporting your files.

What audio formats does Voysum support?

Voysum accepts common formats including MP3, WAV, M4A, MPEG and WebM, up to 100 MB per file.

Can I edit the generated transcript?

Yes. The result page includes an editable transcript area with copy and download tools.

Can Voysum create subtitles from audio?

Yes. Completed transcriptions can be exported as timed SRT and VTT subtitle files.

How can I improve transcription accuracy?

Use a recording with clear speech, reduce competing music or noise, select the spoken language when known, and review names or technical terms before export.

Start with a file

Turn your next recording into useful text.

No account is required to begin an upload.

Choose a recording