API directory · Speech-to-text API (medical mode add-on)
AssemblyAI API
Public speech-to-text API with a medical mode enabled by parameter, published per-hour prices, published streaming rate limits and a public sample BAA.
Short answer
What does the AssemblyAI API give a developer?
Public speech-to-text API with a medical mode enabled by parameter, published per-hour prices, published streaming rate limits and a public sample BAA.
Base URL: https://api.assemblyai.com (EU: api.eu.assemblyai.com)
Auth: Authorization header carrying the API key
Cite as: AssemblyAI API listing, Compare Healthcare API, last reviewed 2026-09-01.
Endpoints
Copied from the vendor's own reference. Where a path is described rather than published, the description is what the vendor states.
| Method | Endpoint | Mode | Purpose |
|---|---|---|---|
| POST | /v2/transcript | Batch | Submit pre-recorded audio asynchronously; poll or use a webhook for completion. |
| POST | https://sync.assemblyai.com | Batch | Synchronous transcription for short audio. |
| WS | wss://streaming.assemblyai.com/v3/ws | Streaming | Real-time streaming transcription (v3; the v2 realtime endpoint is inactive). |
| WS | wss://agents.assemblyai.com/v1/ws | Streaming | Voice agent API for conversational flows. |
Published rate limits
Numbers the vendor states publicly. Anything unpublished should be made contractual before you plan capacity.
| Streaming, free tier | 5 new sessions per minute |
|---|---|
| Streaming, paid | 100+ new sessions per minute, auto-scaling +10%/min above 70% utilisation |
| Pre-recorded concurrency | Account-tier parallel job cap — confirm your account's number in the docs |
Published pricing
List prices as published on the vendor's own pricing page at the verification date. Follow the source link before you quote these to anyone.
| Universal-3.5 Pro, pre-recorded | $0.21/hour |
|---|---|
| Universal-3.5 Pro, realtime | $0.45/hour |
| Universal-Streaming | $0.15/hour |
| Medical mode add-on | +$0.15/hour on all models (domain=medical-v1) |
| Free credit | $50, no credit card required |
Data handling and compliance
The three answers a health-system security review will ask you for, as published.
| BAA | Sample BAA published publicly; execution through sales |
|---|---|
| Retention | Configurable TTL on audio and transcripts via data controls |
| Training on PHI | Opt-out of the model-improvement programme available in data controls |
How to integrate the AssemblyAI API
An ordered path based on the public documentation, written for an engineering team scoping the work.
- 01
Create a key
Sign up and take the $50 credit; no sales contact is required to reach production pricing.
- 02
Enable medical mode
Set domain=medical-v1 on a Universal model and re-run your own audio to see the delta on clinical vocabulary.
- 03
Use webhooks
Register a webhook on /v2/transcript instead of polling, and verify it before trusting completion events.
- 04
Set data controls
Set the audio and transcript TTL and opt out of model improvement before any PHI touches the API.
- 05
Stream for live encounters
Move to the v3 streaming socket and budget for session-per-minute limits at your peak clinic hour.
- 06
Own the note
Structure, templates and clinical review remain your build — the API returns transcript, not documentation.
What the documentation does not warn you about
The judgement an endpoint list cannot give you.
The most builder-friendly documentation among the general ASR vendors for this use case, and still a build-your-own-note architecture with the whole evaluation burden that implies.
Primary sources for this listing
Every fact above traces to one of these pages. If one has changed, tell us and the listing is re-verified.
- Pricing https://www.assemblyai.com/pricing
- Streaming rate limits https://www.assemblyai.com/docs/streaming/rate-limits
- Submit transcript endpoint https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/submit
- Sample BAA https://www.assemblyai.com/legal/business-associate-agreement
- Data controls https://www.assemblyai.com/docs/data-controls
Evidence & sources
Standards the integration steps above assume. Vendor-specific evidence is the primary source list on this page.
U.S. Department of Health & Human Services · Regulation · Tier A — primary documentation
Supports: The contractual clauses a documentation vendor's BAA must contain.
U.S. Department of Health & Human Services · Regulation · Tier A — primary documentation
Supports: Administrative, physical and technical safeguards a vendor handling recorded encounter audio must implement.
HL7 International · Standard · Tier A — primary documentation
Supports: Resource definitions (DocumentReference, Composition, Encounter, Condition, MedicationRequest) that clinical documentation output must map onto.
Source tiers are defined on the methodology page. Outbound links are unaffiliated and carry no commercial relationship.
Frequently asked questions
- Does AssemblyAI have a public API?
- Public speech-to-text API with a medical mode enabled by parameter, published per-hour prices, published streaming rate limits and a public sample BAA.
- How do you authenticate with the AssemblyAI API?
- Authorization header carrying the API key
- What are the AssemblyAI API rate limits?
- Streaming, free tier: 5 new sessions per minute. Streaming, paid: 100+ new sessions per minute, auto-scaling +10%/min above 70% utilisation. Pre-recorded concurrency: Account-tier parallel job cap — confirm your account's number in the docs
- How much does the AssemblyAI API cost?
- Universal-3.5 Pro, pre-recorded: $0.21/hour. Universal-3.5 Pro, realtime: $0.45/hour. Universal-Streaming: $0.15/hour. Medical mode add-on: +$0.15/hour on all models (domain=medical-v1). Free credit: $50, no credit card required
- Can you evaluate AssemblyAI without a sales conversation?
- Yes — self-serve key, $50 credit, published prices and public scribe recipes