AudioBurner
Speech to text on our own GPUs, wire-compatible with AssemblyAI: switch by changing the base URL and key.
Private beta: sign-up is not open yet.
What it is
AssemblyAI-compatible speech to text: the v3 streaming WebSocket for live audio and the v2 batch REST API for files. It runs in our own AWS account, so your audio stays on servers we control.
What works today
- Live, English: words carry one word entry per finished turn, no per-word timings.
- Batch: words carry a start and end time for every word.
- Add-ons on: Summary, Keyterms.
- Switched off (a request for one is refused): Speaker labels, PII redaction.
Prices
| Product | Price | Notes |
|---|---|---|
| Live, English | $0.12 an hour | billed by connection seconds |
| Batch | $0.09 an hour | billed by audio seconds per channel |
| Add-on: Summary | +$0.05 an hour | on batch |
| Add-on: Keyterms | +$0.00 an hour | on live, batch |
1 credit = 1 US cent at list price; billed by the second.
Plans
| Plan | Monthly | Included | At once |
|---|---|---|---|
| Pay as you go | $0 a month | 0 credits | 5 live, 5 batch |
| Starter | $25 a month | 3000 credits | 10 live, 10 batch |
| Pro | $100 a month | 13000 credits | 25 live, 25 batch |
| Business | $400 a month | 56000 credits | 100 live, 50 batch |
- Included credit expires at each renewal; bought top-ups never expire; downgrade at renewal, no refund.
- Annual plans: coming soon, not available during beta.
Switch from AssemblyAI
Keep your AssemblyAI client. Change the host and the key; the messages are the same.
Live (v3 streaming): wss://streaming.audioburner.io/v3/ws ; mint a browser token from GET https://api.audioburner.io/v3/tokenBatch (v2): POST https://api.audioburner.io/v2/transcript with an audio_url we can fetch; poll GET https://api.audioburner.io/v2/transcript/<id>
Private beta: sign-up is not open yet. Keys are not issued to the public yet.
For agents
- /llms.txt: everything on this page, plus limits and refusals.
- /v1/prices: the price table as JSON.