Skip to content
AssemblyAI logo

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.

Written by Compare Healthcare API Editorial DeskReviewed by Technical ReviewLast reviewed Rubric v1.0
Verified 2026-09-04Self-serve access4 documented endpointsOfficial documentation ↗

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.

MethodEndpointModePurpose
POST/v2/transcriptBatchSubmit pre-recorded audio asynchronously; poll or use a webhook for completion.
POSThttps://sync.assemblyai.comBatchSynchronous transcription for short audio.
WSwss://streaming.assemblyai.com/v3/wsStreamingReal-time streaming transcription (v3; the v2 realtime endpoint is inactive).
WSwss://agents.assemblyai.com/v1/wsStreamingVoice agent API for conversational flows.
AssemblyAI documented endpoints, verified 2026-09-04

Published rate limits

Numbers the vendor states publicly. Anything unpublished should be made contractual before you plan capacity.

Streaming, free tier5 new sessions per minute
Streaming, paid100+ new sessions per minute, auto-scaling +10%/min above 70% utilisation
Pre-recorded concurrencyAccount-tier parallel job cap — confirm your account's number in the docs
AssemblyAI published limits

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
AssemblyAI published pricing

Data handling and compliance

The three answers a health-system security review will ask you for, as published.

BAASample BAA published publicly; execution through sales
RetentionConfigurable TTL on audio and transcripts via data controls
Training on PHIOpt-out of the model-improvement programme available in data controls
AssemblyAI data handling

How to integrate the AssemblyAI API

An ordered path based on the public documentation, written for an engineering team scoping the work.

  1. 01

    Create a key

    Sign up and take the $50 credit; no sales contact is required to reach production pricing.

  2. 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.

  3. 03

    Use webhooks

    Register a webhook on /v2/transcript instead of polling, and verify it before trusting completion events.

  4. 04

    Set data controls

    Set the audio and transcript TTL and opt out of model improvement before any PHI touches the API.

  5. 05

    Stream for live encounters

    Move to the v3 streaming socket and budget for session-per-minute limits at your peak clinic hour.

  6. 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.

Evidence & sources

Standards the integration steps above assume. Vendor-specific evidence is the primary source list on this page.

  1. U.S. Department of Health & Human Services · Regulation · Tier A — primary documentation

    Supports: The contractual clauses a documentation vendor's BAA must contain.

  2. 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.

  3. 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

Continue