Transcription API for law firms and legal teams
Depositions, client calls, recorded hearings and intake interviews turned into timestamped text your team can search, quote and hand to a drafting tool — without a per-seat dictation subscription or a per-minute human service on every file.
So far: 1,073 recordings and 67,528 minutes through the API since April 2026, across 20 keys, 13 of them held by developers outside the team.
- Step 1Deposition audio, client call, hearing recording
- Step 2POST /api/v1/transcribe · word timestamps
- Step 3Timestamped transcript · SRT · DOCX · summary + quotes
- Step 4Prep memo, exhibit index, searchable matter file
From recording to business result: one POST, one poll, every output format from the same job.
Three things a legal business actually does with it
Each priced at the published rate — $6 per 500 minutes — $0.72 an audio hour, $0.29 on the 5,000-minute pack — as credits that never expire.
A 4-hour deposition recording goes in the moment it ends. Soon after, the associate has a transcript with word-level timestamps, a summary and pulled quotes — enough to draft the prep memo before the certified transcript arrives.
Intake and update calls recorded with consent post to the API automatically. The transcript and a summary land in the matter folder, so the file has a record of what was said without anyone typing a note.
Years of hearing and arbitration recordings sit on a drive nobody opens. Run the archive once through the batch connector and every recording becomes text you can search across matters.
What you can rely on — and what we are not
Whipscribe produces working transcripts for preparation and review. It is not a certified court reporter and its output is not the official record. Use it to draft faster; order the certified copy for filing.
30 days on free, 365 on paid, and any file can be deleted on demand from its page. Nothing is used to train a model.
Transcription runs on our own servers. Audio is never forwarded to OpenAI or any third-party model — usually the first question a client will ask.
Rev, TranscribeMe and GoTranscript legal rates, and when a certified human transcript is needed, are compared on legal transcription services.
The whole integration
Two calls. No SDK to learn, no model to host, no GPU to rent.
# submit — returns a job id immediately curl -X POST https://whipscribe.com/api/v1/transcribe/url \ -H "X-API-Key: $KEY" \ -H "Idempotency-Key: legal-$RECORDING_ID" \ -H "Content-Type: application/json" \ -d '{"url":"https://example.com/recording.mp3","word_timestamps":true}' → 202 {"job_id":"a1b2…","status":"queued"} # poll, then collect — every format from the one job curl "https://whipscribe.com/api/v1/jobs/$JOB" -H "X-API-Key: $KEY" curl "https://whipscribe.com/api/v1/jobs/$JOB/result?format=docx" -H "X-API-Key: $KEY" curl "https://whipscribe.com/api/v1/jobs/$JOB/insights" -H "X-API-Key: $KEY" # summary · quotes · topics
Wire it into what you already use
What it replaces or sits beside
Vendors legal teams compare us with — each has a side-by-side page.
Try it on a real recording before you build anything
Drop a file from your own business. a pack from $6 (500 minutes) opens the full transcript — that is how to check accuracy on your audio before writing code.
Questions legal teams ask
Is a Whipscribe transcript admissible in court?
No. It is a working transcript for preparation, not a certified record. Certified transcripts come from a licensed court reporter; use Whipscribe to start drafting while you wait for one.
Can we transcribe a recording with several speakers?
Yes, in the summary, key quotes and chapters: WhipScribe names the speakers there; every segment carries word-level timestamps, so counsel can find and cite each exchange.
What about privilege and confidentiality?
Audio is processed on servers we operate, never sent to a third-party model, never used for training, and deleted on demand. You keep the retention decision; we do not make it for you.
What does transcription cost for a legal business?
$6 per 500 minutes — $0.72 an audio hour, $0.29 on the 5,000-minute pack — as credits that never expire. The first 20 minutes of any recording are free; a pack transcribes the rest and opens every export. There are no seats and no monthly minimum: a 3-hour recording is about $2.16 of a $6 pack, two hundred half-hour calls about $36 (a $24 pack and a $12 pack), a thousand-hour archive about $288 once.
Is there a free tier on the API?
No recurring free tier. Without a key you can run 3 sample transcriptions a day, and each returns a preview. In the web app every recording gets a free preview, and a pack from $6 (500 minutes) opens the full transcript — which is how to check accuracy on your own audio before paying more.
How do we get an API key?
API keys come with the 5,000-minute pack ($24) or Workspace ($19/month). Then sign in and create the key at /apis/keys — no email, no sales call. Up to 10 active keys per account; rotate and revoke yourself.
How do results come back?
Submit, store the job id, poll GET /api/v1/jobs/{id} until done, then pull txt, json, srt, vtt or docx from the same job. Self-serve keys collect by polling; signed webhooks are an Enterprise feature.
Where is our audio processed?
On servers we operate, in a private, secured cloud. It is never forwarded to OpenAI or any third-party model, and never used for training.
How long is audio kept?
30 days on the free plan, 365 on paid, and any file can be deleted on demand from its page. Wire deletion into your own retention rule if you need it automatic.
Does it label who is speaking?
Yes, in the summary, key quotes and chapters: WhipScribe names the speakers there; every segment carries word-level timestamps, so you can align it with your own speaker data.
What languages does it handle?
99+ languages, auto-detected, or set explicitly. Set it when you know it — auto-detect on a short or noisy clip is the most common cause of a wrong-language transcript.
Can we automate it with tools we already use?
Yes — Zapier, Make, n8n, Airtable, Drive, Dropbox, S3, Zoom, Slack, Notion. Each integration page carries the platform's real step timeout and the submit-then-poll shape that survives it.
What about very long or very large recordings?
Files go up to 10 hours or 5 GB each and are submitted whole, so timestamps stay coherent — nothing is chunked. Hand us a URL and let us fetch it rather than streaming it through a no-code platform.
Do we get a summary as well as the transcript?
Yes. GET /api/v1/jobs/{id}/insights returns a summary, key quotes, topics and speakers for the same job, at no extra charge.
Can we try it before building anything?
Yes — the widget on this page. Drop a real recording from your business; a pack from $6 (500 minutes) opens the full transcript, and you will know whether the accuracy is there before writing a line of code.
Demand behind this page — GSC 90d: 'deposition services transcription', 'attorney dictation service', 'ftr court recording', 'us legal support' — 49 queries, 153 impressions, position 44.7, 0 clicks. The demand is for prep work, and the pages that exist target the consumer app.
Choosing a transcription service?
For teams deciding where recordings go: see our transcription service with prices and turnaround, audio transcription services and the best transcription services side by side.