AI audio transcription
Upload an MP3, WAV, M4A, or video file and get an accurate, timed transcript in minutes. Supports long recordings — no clip limits.
Audio transcript editor
Audio transcription with a real transcript editor
Transcribe audio to text with AI, then edit the transcript with word-level timestamps and click-to-play. Export to SRT, VTT, or TXT in 98+ languages — free to start, with no per-minute fees.
No credit card to start · Long recordings welcome · One flat plan, not per-minute
Everything you need to transcribe and edit audio
A real transcript editor
Fix words inline, split and merge blocks, and read along with word-level timestamps. The transcript stays in sync with your audio.
Click-to-play playback
Click any word or block to jump straight to that moment in the audio, so proofreading and editing are fast.
AI summary & key points
Turn a finished transcript into a clean summary and key points — great for show notes, recaps, and meeting minutes.
Export anywhere
Export your transcript as subtitle files (SRT, VTT) or plain-text documents — ready for video, blogs, or your records.
98+ languages
Transcribe English, Spanish, Mandarin, Cantonese, and 90+ more — with optional translation built into the editor.
From audio to edited transcript in three steps
1
Upload your audio
Drag in a podcast, interview, lecture, voice memo, or video. Your file uploads securely to your project.
2
Auto-transcribe
AI transcribes your audio to text with timestamps. Paid plans unlock Pro transcription for the highest accuracy.
3
Edit & export
Polish the transcript in the editor, generate a summary, then export to SRT, VTT, or TXT.
Transcription without the per-minute meter
Most audio transcription software charges by the minute or by credits, so longer podcasts and interviews get expensive fast. Captioner is built around an editable transcript and one simple plan — transcribe audio to text, fix it in the editor, summarize it, and export it without watching a per-minute counter.
- ✓Word-level timestamps and click-to-play
- ✓Split and merge transcript blocks
- ✓AI summary and key points
- ✓Export SRT, VTT, and TXT
- ✓98+ languages with translation
- ✓Free to start — no per-minute fees
What people transcribe with Captioner
Podcast transcription and show notes
Interview transcription and quotes
Lecture and webinar notes
Meeting minutes and recaps
Repurposing audio into blog posts
Subtitles and captions for video
Audio transcription FAQ
- How do I transcribe audio to text?
- Create an audio project, upload your file, and Captioner transcribes the audio to text automatically. You can then edit the transcript and export it — no software to install.
- Can I edit the transcript after transcription?
- Yes. Captioner is a full transcript editor: correct words inline, split or merge blocks, and click any word to play that moment of the audio. Every edit stays aligned to the original timing.
- What audio and video formats are supported?
- Common audio formats like MP3, WAV, and M4A, plus video files. If it has a clear voice track, Captioner can transcribe it.
- Which languages can it transcribe?
- Over 98 languages, including English, Spanish, Mandarin, and Cantonese. You can also translate the transcript into another language inside the editor.
- Is there a per-minute charge?
- No. Unlike per-minute or credit-based transcription tools, Captioner lets you start free and upgrade to one flat plan — no surprise per-minute or proofreading fees.
- Can I export the transcript as SRT or a document?
- Yes. Export to subtitle files (SRT, VTT) for video, or to a plain-text document for show notes, articles, and records.
- How accurate is the AI transcription?
- Accuracy is strong on clear audio, and the editor makes any cleanup fast with click-to-play and word-level timing. Paid plans add Pro transcription for the highest accuracy.
Ready to transcribe your audio?
Start free, edit the transcript in your browser, and export when you're ready.
Open the audio editor