Skip to content
ScribeCue
Audio to text · Speaker labels

Interviews in, quotes out.

Drop a recording and get a timestamped transcript with speakers you can rename, a summary, and exports in every format — in about a minute.

Drop an audio file here or choose a file
MP3, M4A, WAV, AAC, OGG, FLAC · up to 120 min free
120 free minutes a month

Private: your file is deleted when the transcript is ready (7 days at the latest) and never used to train AI.

120 free minutes / monthNo sign-up or cardFiles auto-deleted
Two microphones whose sound waves become two colour-coded columns of text, one per speakerSPEAKER 1 · 00:42
To convert audio to text, drop an MP3, M4A or WAV file above. ScribeCue transcribes it in about a minute with timestamps and optional speaker labels, and exports TXT, DOCX, SRT or VTT. The first 120 minutes every month are free (files up to 120 minutes), with no account and no watermark. After the free minutes, packs start at $6 for 120 minutes (about $3 per hour of audio), with no subscription.

Built for interviews, meetings and podcasts

  • Speaker labels you can rename, carried into every export.
  • Click any line to hear that moment in your own recording.
  • AI summary and chapters on the finished transcript.
  • Translate the transcript into 24 languages.

Pricing

Pro is $12/month (or $96/year) for 1,500 minutes; minute packs start at $6 for 120 minutes and never renew.

Minutes are only charged for the length of the file, rounded up to the minute, and returned if a job fails.

Frequently asked questions

Is audio to text free?

You get 120 free minutes every month (files up to 120 minutes), no card needed. Pro is $12/month (or $96/year) for 1,500 minutes; minute packs start at $6 for 120 minutes and never renew.

Which file types work?

MP3, M4A, WAV, AAC, OGG, OPUS, FLAC and WebM audio.

How long does it take?

Usually under a minute for a one-hour file.

Does it tell speakers apart?

Yes. Turn on speaker labels before uploading; you can rename Speaker 1, Speaker 2… to real names and the names appear in every export.

Which languages are supported?

Over 30, including English, Spanish, French, German, Portuguese, Hindi, Japanese, Korean and Chinese. Leave it on Auto-detect or pick one.

What happens to my file?

It is stored privately, deleted as soon as the transcript is ready (7 days at the latest), and never used to train AI models. You can delete the transcript any time.

What if the transcription fails?

The minutes are returned to your balance automatically.

More tools and guides