AI audio to text

Audio to text, with every speaker named

Upload an MP3, WAV, M4A or video file — or record straight in the browser — and MinutesMaster turns it into a timestamped transcript with speakers separated by voice, followed by a summary, decisions and action items. 38 languages, mixed-language recordings included.

5 free credits (2.5 hours of audio) · No credit card · No AI training on your data

More than an audio to text converter

A plain converter gives you a wall of words. MinutesMaster gives you a transcript you can read: the recording is split into speaker turns, each with a timestamp, and the voices are separated so you can see who said what. Give a speaker their real name once and it changes everywhere — in the transcript, the minutes and every export.

Because the transcript is the start, not the end, MinutesMaster also writes minutes from the same recording: a summary, the topics, decisions and action items with owners. You can translate the transcript or the minutes into any of the 38 supported languages, and the translation is kept next to the original.

Files up to 2 GB are accepted, audio or video. Pricing is per recording: 1 credit covers 30 minutes of audio, and a new account starts with 5 free credits — 2.5 hours — without a credit card.

minutesmaster.ai/dashboard/trials/…
CompletedUpload · interview.m4a · 52 min · English
Customer interview — onboarding

Maria Lopez (11:48) — Honestly, the setup took longer than the trial. We needed two calls with support before the first import worked.

Jonas Berg (12:20) — That’s useful. Which step took the longest — connecting the data source or mapping the fields?

Decision

Onboarding friction is the top theme to bring to the product review.

Action item

Jonas Berg → share the interview summary with the product team

People
Maria Lopez — Customer
Jonas Berg — Researcher
Translations
ENDECSPL

The transcript and summary, translated into German, Czech and Polish, export as Word or PDF.

Export
PDFDOCXTXTSRTVTTJSON
How it works

From audio file to text in four steps

Works the same for an interview, a lecture, a voice memo or a recorded meeting.

  1. 1

    Create a free account

    Sign up with your email — no credit card. Your account starts with 5 credits, enough for 2.5 hours of audio.

  2. 2

    Upload or record

    Drop in an audio or video file (MP3, WAV, M4A, FLAC, AAC, OGG, MP4, MOV, MKV, WebM and more, up to 2 GB), record in the browser or the mobile app, or paste a YouTube or Google Drive link.

  3. 3

    Get the transcript

    MinutesMaster transcribes the recording in its own language, separates the speakers by voice and adds timestamps. Mixed-language audio is handled without choosing a language first.

  4. 4

    Edit, translate and export

    Rename speakers, fix a word, translate if you need another language, then export the text as TXT, Word (DOCX), PDF, JSON or SRT/VTT subtitles.

Features

What you get from every recording

A transcript you can work with, not just text you have to clean up.

  • Most audio and video formats

    MP3, WAV, M4A, FLAC, AAC, WMA, OGG, MP4, MOV, AVI, MKV, WMV, FLV and WebM, up to 2 GB per file. No converting before you upload.

  • Speakers separated by voice

    Each turn is labelled with its speaker and a timestamp. Give a speaker a name once and it is used throughout the transcript and the exports.

  • Readable turns

    The text is grouped into whole speaker turns instead of fragments, so a long recording reads like a script rather than a stream of lines.

  • 38 languages

    Czech, Slovak, Polish, Hungarian, Romanian, Ukrainian, German, English and 30 more, including recordings that switch between languages. Translate the result into any of them.

  • Text, Word, PDF and subtitles

    Export plain text or DOCX for editing, PDF for sharing, JSON for other tools, and SRT or VTT subtitles with timestamps for video.

  • Minutes from the same audio

    Alongside the transcript you get a summary, decisions and action items with owners — useful when the recording was a meeting rather than a monologue.

Use cases

What people convert to text

Anything recorded that someone would otherwise have to listen to again.

  • Interviews and research

    Qualitative interviews, thesis research and user studies become transcripts with speaker names and timestamps you can quote from.

  • Recorded meetings

    A recording from a phone, a dictaphone or a meeting platform becomes a transcript plus minutes with decisions and action items.

  • Lectures, talks and podcasts

    Long recordings get a searchable transcript and a summary of the main points, in the original language or a translation.

  • Video that needs subtitles

    Upload the video file and export SRT or VTT subtitles with timestamps, ready to add to a video player or editor.

FAQ

Frequently asked questions

How do I convert audio to text?
Create a free account, upload the audio or video file and wait for processing to finish. MinutesMaster transcribes the recording, separates the speakers by voice and adds timestamps. You can then edit the text and export it as TXT, Word, PDF, JSON or subtitles.
Is the audio to text converter free?
You can start for free: new accounts get 5 credits, which cover 2.5 hours of audio, without a credit card. After that, credit packs start at 10 credits for €9, and the Pro plan is €19 a month for 40 credits. One credit covers 30 minutes of audio.
Which audio and video formats can I upload?
MP3, WAV, M4A, FLAC, AAC, WMA, OGG and video files such as MP4, MOV, AVI, MKV, WMV, FLV and WebM, up to 2 GB per file. You can also record in the browser or paste a YouTube or Google Drive link.
Can I convert MP3 to text in Czech, Polish or another language?
Yes. Transcription works in 38 languages, including Czech, Slovak, Polish, Hungarian, Romanian, Ukrainian and German, and recordings that mix languages are handled without choosing a language first.
Does the transcript show who is speaking?
Yes. Speakers are separated by voice and every turn has a timestamp. Rename a speaker once and the name is applied to the whole transcript, the minutes and all exports.
Can I translate the transcript?
Yes. The full transcript and the minutes can be translated into any of the 38 supported languages. Each translation is kept next to the original and exports the same way.
Is my audio used to train AI?
No. MinutesMaster does not use recordings, transcripts or minutes to train AI models. Your recordings are private to your account unless you share them with a team, and you can delete them at any time.

Turn your next recording into text you can use

Upload a file and get a transcript with speaker names and minutes — 5 free credits, no credit card.

  • 5 free credits
  • No credit card
  • No AI training on your data

Last updated