Drop a field recording, a Zoom MP4, or paste a URL. Multi-speaker transcript with timestamps every 30 seconds, one-click quote extraction, DOCX export. Built for journalists, oral historians, qualitative researchers. Packs from $4, credits never expire · instant preview with no signup · free account adds 60 minutes.
How it works
Built for the journalism + research workflow — speaker fidelity, citation timestamps, and the formats your editor or thesis advisor expects.
Field-recorder WAV, phone-recorded M4A, Zoom MP4, or a hosted URL. Up to 2 GB per file in the browser; larger files via API.
Automatic diarisation labels every voice. Rename Speaker 1 to Reporter and Speaker 2 to Source after the transcript loads — names persist across exports.
One click for a quote list — strongest statements, attributed, timestamped. One click for a DOCX hand-off ready for your editor or thesis chapter.
What you can do with the transcript
Every interview transcript opens with an AI sidebar tuned for long-form Q&A.
Pull-quote candidates surfaced automatically — attributed to a speaker, timestamped, ready for a deck card or a story headline.
Word-level timestamps on every line. Hover any sentence for the exact second; click to jump back to the audio.
Ask “every time the source mentions funding” or “list all named individuals.” The AI answers with quoted timestamps.
DOCX for an editor, TXT for a quick draft, JSON for a research database. SRT/VTT if you're cutting an explainer video around the audio.
Pricing
A 30-minute interview is free. A 1-hour profile interview runs about $2. A 3-hour roundtable is $6. Prorated to the second; no monthly subscription; credits never expire.
FAQ
Drop the audio or video file above, or paste a URL. Multi-speaker transcript with timestamps returns in about a minute per 30 minutes of audio. Preview with no signup; a free account (60 minutes included) unlocks the full text.
Yes. Automatic diarisation labels every voice; rename Speaker 1 to Reporter and Speaker 2 to Source after the transcript loads. Three-plus voices handled the same way.
Yes. Whipscribe stamps every 30 seconds by default for skimmability, with word-level timestamps on every line for citation precision.
Yes. One click after the transcript loads produces a quote list with speaker attribution and timestamps.
Yes. Open-source Whisper on private infrastructure. Audio is never sent to OpenAI, Google, or any third-party transcription service, and we never train models on your audio. TLS 1.3 in transit, AES-256 at rest.
MP3, M4A, WAV, FLAC, MP4, MOV, MKV. Field-recorder WAV from Zoom H1n/H6 works directly.
Yes. DOCX with speaker labels and timestamps included on every pack. TXT, SRT, VTT, JSON also included.
Instant preview, no signup, no card. A free account includes 60 minutes.