Quebec transcribes English audio, or aligns a transcript you already have, and gives every word a start and end time. https://quebec.yarn.so/llms.txt (the write-up, with these docs at the end, is at https://quebec.yarn.so) It costs $0.32 per hour of audio, billed by the second. Failed requests are free. English only, up to 60 minutes and 1 GB per file. An hour of audio takes about a minute. 1. Create a key curl -X POST https://quebec.yarn.so/keys -> 201 {"api_key": "qb_123_...", "balance_usd": 0, "top_up_url": "https://quebec.yarn.so/top-up/123"} There is no signup. Save the key somewhere secret, because it is shown only once. If you lose it, email help@yarn.so from the address you verified or paid with and we'll move the balance to a new key. 2. Add credit Open top_up_url in a browser to pay $10 by card. Add ?amount=25 or ?amount=100 to pay more. /balance gives you the link again. A company email gets $5 free: curl https://quebec.yarn.so/credit -H "Authorization: Bearer qb_123_..." \ -H "Content-Type: application/json" -d '{"email": "jo@acme.com"}' -> 202 {"status": "verification_sent"} We email a link, and the $5 is added when it's opened. Once per company, and not for Gmail or other free addresses. 3. Transcribe curl https://quebec.yarn.so/transcribe -H "Authorization: Bearer qb_123_..." -F file=@talk.mp3 -> 200 {"text": "Hello, there.", "duration": 2.0, "words": [{"text": "Hello,", "start": 0.43, "end": 0.88, "speaker": "speaker_0"}, ...], "cost_usd": 0.000178, "balance_usd": 9.999822, "timings": {"transcribe": 1.2, "align": 0.9, "total": 2.1}} Any common audio or video format works. Times are in seconds. 4. Or align a transcript you already have curl https://quebec.yarn.so/align -H "Authorization: Bearer qb_123_..." -F file=@talk.mp3 \ -F text="Hello, there." -> 200 {"duration": 2.0, "words": [{"text": "Hello,", "start": 0.43, "end": 0.88}, ...], "cost_usd": 0.000178, "balance_usd": 9.999822, "timings": {"total": 1.9}} text is the plain transcript, with no speaker labels or timestamps. Each word comes back with its times, in order. 5. Check the balance curl https://quebec.yarn.so/balance -H "Authorization: Bearer qb_123_..." -> 200 {"balance_usd": 9.999822, "top_up_url": "https://quebec.yarn.so/top-up/123"} Errors look like {"error": {"code": "...", "message": "..."}}. 401 invalid_key The Authorization header is missing or the key is unknown. 402 insufficient_balance The balance is $0 or less. error.top_up_url is the link to add credit. 400 missing_file No form field named "file". 400 missing_text /align needs the transcript in a form field named "text". 400 too_many_fields More than 5 form fields besides the file. 400 unreadable_audio The file could not be read as audio. 400 invalid_amount ?amount= must be 10, 25 or 100. 400 invalid_email /credit needs JSON like {"email": "jo@acme.com"}. 404 not_found No such route, or no account for that top-up link. 409 not_eligible error.reason says why: free_email_domain, key_already_credited, domain_already_credited, recently_sent (the company got a link in the last day) or key_recently_sent (this key did). 409 credit_unavailable Free credit is switched off for now. 413 too_long Over 60 minutes of audio. 413 too_large Over 1 GB of audio, or over 1 MB of text. 413 too_much_text /align got more than 10 words per second of audio. 429 busy We're at capacity. Wait Retry-After seconds and try again. 502 failed The request failed and nothing was charged. Try again. 500 internal_error Something else went wrong. Try again. How accurate it is We tested on hand-labelled speech from the Buckeye corpus, which Quebec never saw in training. Boundaries within 20 ms Bad cuts Quebec 75% 11% MFA 3.x 61% 19% ElevenLabs Cue 30% 39% WhisperX 24% 49% A bad cut means deleting one word takes more than 50 ms off the next word, or leaves more than 50 ms of the deleted word behind. Two people labelling the same speech agree within 20 ms about 79% of the time (Goldman 2011, on a different corpus), so that's roughly the ceiling. Quebec runs on MFA's acoustic model and Whisper tiny's features. How it works: https://quebec.yarn.so Who we are Quebec is made by Yarn (https://yarn.so), a video editor that teams at Clay, Faire and Front use to make product demos and launch videos. Quebec is the transcript aligner we built to make editing more accurate for our customers, and we're now sharing it publicly at cost. We're backed by Y Combinator, General Catalyst and Race Capital. Questions go to help@yarn.so.