API directory · Speech-to-text platform (cloud or on-premises)
Speechmatics API
Batch and real-time speech-to-text with published plan concurrency and the category's clearest self-hosting story — the option that keeps audio inside your own perimeter.
Short answer
What does the Speechmatics API give a developer?
Batch and real-time speech-to-text with published plan concurrency and the category's clearest self-hosting story — the option that keeps audio inside your own perimeter.
Base URL: https://asyncbatch.speechmatics.com · realtime: wss://eu.rt.speechmatics.com/v2/ (or global.rt)
Auth: API key on every request; unauthenticated calls return HTTP 401
Cite as: Speechmatics 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/jobs | Batch | Create a batch transcription job. |
| GET | /v2/jobs/{id}/transcript | Batch | Retrieve the completed transcript. |
| WS | wss://<region>.rt.speechmatics.com/v2/ | Streaming | Real-time transcription with diarisation and partials. |
Published rate limits
Numbers the vendor states publicly. Anything unpublished should be made contractual before you plan capacity.
| Free plan | 2 concurrent real-time sessions |
|---|---|
| Pro plan | 50 concurrent real-time sessions; 10 batch jobs per second |
| Enterprise | No published rate limits — custom |
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.
| Pro tier | $0.129 per hour (list, at time of verification) |
|---|---|
| Model-training discount | 33% discount if you opt into the model-improvement programme — do not take this for PHI audio |
| Volume discounts | 20% automatically above 500 hours/month per STT type; further tiers from 24,000 hours/year |
| Free credit | $100, no credit card required |
Data handling and compliance
The three answers a health-system security review will ask you for, as published.
| BAA | HIPAA claimed alongside SOC 2 Type II and ISO/IEC 27001:2022; DPA and sub-BAA via the trust centre |
|---|---|
| Retention | Not opted into training: real-time audio never stored; batch data auto-deletes after 7 days or sooner via API |
| Training on PHI | Only if you opt into the discount programme — the default is no training |
How to integrate the Speechmatics API
An ordered path based on the public documentation, written for an engineering team scoping the work.
- 01
Take the free credit
Sign up self-serve and transcribe your own clinical audio before any commercial conversation.
- 02
Decline the training discount
The 33% discount is conditional on model-improvement rights. For PHI audio that trade is not available to you.
- 03
Pin your region
Use a region-pinned realtime endpoint rather than the global router when data residency is contractual.
- 04
Test accents and settings
Accent and far-field robustness is the reason to shortlist Speechmatics — test it on your hardest recordings, not clean audio.
- 05
Scope on-premises early
If a customer refuses cloud processing, price the container deployment before you promise it.
- 06
Plan the note layer
Clinical structuring, templates and review are yours; this is a transcription platform.
What the documentation does not warn you about
The judgement an endpoint list cannot give you.
The on-premises container is the differentiator and the reason to keep Speechmatics on a shortlist — it is one of few ways to keep audio inside your own perimeter. Everything above the transcript is still your build.
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.
- Documentation https://docs.speechmatics.com
- Authentication https://docs.speechmatics.com/get-started/authentication
- Realtime WebSocket reference https://docs.speechmatics.com/api-ref/realtime-transcription-websocket
- Pricing, plans and concurrency https://www.speechmatics.com/pricing
- Plans https://docs.speechmatics.com/administration/plans
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 Speechmatics have a public API?
- Batch and real-time speech-to-text with published plan concurrency and the category's clearest self-hosting story — the option that keeps audio inside your own perimeter.
- How do you authenticate with the Speechmatics API?
- API key on every request; unauthenticated calls return HTTP 401
- What are the Speechmatics API rate limits?
- Free plan: 2 concurrent real-time sessions. Pro plan: 50 concurrent real-time sessions; 10 batch jobs per second. Enterprise: No published rate limits — custom
- How much does the Speechmatics API cost?
- Pro tier: $0.129 per hour (list, at time of verification). Model-training discount: 33% discount if you opt into the model-improvement programme — do not take this for PHI audio. Volume discounts: 20% automatically above 500 hours/month per STT type; further tiers from 24,000 hours/year. Free credit: $100, no credit card required
- Can you evaluate Speechmatics without a sales conversation?
- Yes — self-serve signup with $100 credit; enterprise and on-premises via sales