Timestamps on every utterance
Jump-to-time on every line lets you link the published quote straight back to the source audio in your CMS or fact-check trail.
Six export formats out of the box
SRT and VTT for video packages. DOCX and PDF for print. TXT and JSON for headless and editorial workflows. Switch formats with one click.
99+ languages for field recordings
Cover sources in their own language. Our AI transcription handles regional accents your field-recorder picks up across 99+ supported languages.
How it works
From recording to ready-to-share in three steps
Upload your field audio
Drop in any common audio or video format. Phone recordings, Zoom interviews, in-person scrums, and field captures all work.
Get a speaker-labeled transcript
Speaker detection separates your voice from the source. Quotes are pre-formatted with timestamps so attribution is unambiguous.
Export in your editorial format
Pull SRT or VTT for the video desk, DOCX for print, JSON for a headless workflow. Every format keeps timestamps intact.
99% accuracy in 99+ languages, built for international field reporting.
- 99%
- Accuracy
- 99+
- Languages supported
- ~90 sec
- From upload to transcript
- Anytime
- Cancel, no contract
Simple pricing
Free for files up to 30 minutes, no card needed. Paid plans start at $14.99.
Free
- Every file on our premium engine, with speaker detection and top accuracy
- 30 free transcriptions every day, each up to 30 minutes, and your first file up to an hour with an AI summary
- Free TXT download, plus copy and edit every transcript
Cancel anytime. Try the free plan before you upgrade. See all plans
Frequently asked questions
Everything you need to know about the AI Agent for Media and Journalism
SRT for broadcast workflows, VTT for web-embedded video. Both formats preserve speaker labels and exact timestamps so your video editor can cut to the quote directly.
Our AI transcription reaches up to 99% accuracy on clear audio. For any quote that will appear in print or broadcast, we recommend confirming the exact wording against the source audio. The jump-to-time link on every line makes this a 5-second check.
Yes. The transcript editor lets you replace a speaker label across an entire interview in one action, so you can mark a source as Source A or redact a name from a sensitive field recording.
Yes. Our AI transcription supports 99 languages including Spanish, French, Arabic, Mandarin, Hindi, Portuguese, and German. Regional accents are handled natively without per-call configuration.
Ready to give your workflow an upgrade?
Join the professionals saving hours every week with AI-powered transcription.