Muse Voice

Muse Voice turns audio and video into a searchable transcript with speaker labels and word-level timestamps. Upload a file, record directly in the browser, or paste a hosted media link to start transcription—then review the draft as timed text so you can quickly verify what was said.

The workspace supports speaker diarization, letting you rename speakers (like “Speaker 1”) once and apply the change across the transcript. Each word includes a timestamp you can jump to, making it easier to correct misheard names, numbers, or disputed phrases before you deliver the final output.

Muse Voice is designed for practical transcription workflows—interviews for journalism and qualitative research, meeting recordings for notes and documentation, podcast episodes for show notes, and video files where you need subtitle-capable formats. It also supports multilingual recognition with auto-detected language selection or manual language choice.

Exports come in six formats so you can use the same corrected transcript in different ways: TXT, DOCX, PDF, SRT, VTT, or JSON. New accounts include 5 free minutes, and you can choose Starter, Pro, or Max plans with yearly minute allowances and recurring or one-time minute packs.

What can I transcribe in Muse Voice?

You can transcribe audio or video by uploading a supported file, recording live in the browser, or pasting a supported hosted media URL. File uploads support common formats like MP3, WAV, M4A, MP4, MOV, and WEBM (up to 1 GB per file).

Does Muse Voice show timestamps and speaker labels?

Yes. Transcripts include speaker labeling (with speaker separation enabled) and word-level timestamps so you can review the text against exact moments in the recording.

Can I rename “Speaker 1” and have it update everywhere?

Yes. Rename a generic speaker label once and the change applies across matching segments and the exports that you generate from your corrected transcript.

Which export formats are available?

You can export the corrected transcript as TXT, DOCX, PDF, SRT, VTT, or JSON—use subtitles (SRT/VTT) and structured timing data (JSON) when you need them.

How many free minutes do I get?

New Muse Voice accounts start with 5 free transcription minutes. Use them to test a short representative recording end-to-end (intake, review, and export).

Where does transcription happen, and can I control my uploaded recordings?

Transcription runs server-side. Your media and transcripts remain in your account until you delete them, and deleting a recording removes both the recording and its transcript from your account.