Vendor profile · Speech-to-text with deployment flexibility
Speechmatics review
Accuracy- and language-focused speech-to-text with on-premise and container deployment options.
Short answer
What is Speechmatics and who should use it?
Speechmatics is the strongest option when audio never leaves your infrastructure: container and on-premise deployment, wide language coverage and good accent robustness. It is transcription only, so the clinical documentation layer is still yours.
Cite as: Speechmatics vendor assessment, Compare Healthcare API, last reviewed 2026-09-01.
Overview
Deployment flexibility is Speechmatics' distinguishing feature. For buyers whose data governance forbids sending audio to a multi-tenant cloud, self-hosted containers change what is contractually possible.
Language breadth and accent robustness are genuine strengths for multinational products. As with other ASR vendors, none of the clinical structuring work is included.
Integration surface
What an engineering team is actually buying: the API posture, how you authenticate, what you send and what comes back.
| API posture | Public developer API |
|---|---|
| What the API does | Speech-to-text platform with strong accent and language coverage, available as cloud API or on-premises container deployment. |
| Authentication | API key for cloud; licensed container for self-hosted |
| Transport | REST batch jobs and real-time WebSocket transcription |
| Response payload | Transcripts with diarisation and formatting; no clinical documentation layer |
| SDKs / clients | HTTP APIs plus published client tooling |
| Try without a contract | Yes — self-serve trial access |
Official developer resources
- Speechmatics documentationdocs.speechmatics.com
Scores by criterion
Rubric v1.0. Each score is out of 10; the weight is the share of the total.
| Criterion | Weight | Score |
|---|---|---|
| API & SDK maturityCan an engineering team ship against this without a services contract? | 22% | 8.28.2 |
| Clinical accuracy & output qualityDoes the transcript and the resulting note hold up on real clinical audio? | 20% | 7.77.7 |
| EHR & FHIR interoperabilityHow much integration work stands between the output and a chart? | 16% | 3.03.0 |
| Compliance & security postureCan this survive your customer's security review? | 16% | 8.88.8 |
| Latency & streaming behaviourIs it fast enough for the interaction you are building? | 10% | 8.18.1 |
| Specialty & template coverageWill it produce the note your users actually write? | 8% | 6.66.6 |
| Commercial terms & transparencyCan you price your own product on top of it? | 8% | 7.87.8 |
Disclosed facts
Recorded from public documentation. Anything a vendor does not publish is recorded as not disclosed, never estimated.
| Deployment model | Cloud, container and on-premise |
|---|---|
| Pricing model | Published cloud pricing; enterprise terms for self-hosted |
| BAA availability | Discuss with the vendor; self-hosting can remove the need |
| Certifications | Enterprise security posture — confirm current certifications |
| Training on PHI | Self-hosted deployment keeps audio in your environment |
| Streaming support | Yes |
| FHIR / EHR write-back | No |
| White-label rights | Yes — it is infrastructure |
| Self-serve access | Yes for cloud |
Strengths
Where it scores well
- On-premise and container deployment for strict data-governance requirements.
- Very broad language coverage and strong accent robustness.
- Well-documented API for a self-hosted-capable vendor.
Limitations
Where it loses points
- Transcription only — no clinical note generation.
- Self-hosting shifts substantial operational burden to you.
- No healthcare-specific integration or template layer.
Best fit
Products with strict data-residency or on-premise requirements, or heavy multilingual needs.
Evidence & sources
Every factual claim on this page traces to one of the primary references below. Each entry records what it supports and its evidence tier, so documentation can be told apart from judgement.
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.
HL7 International · Standard · Tier A — primary documentation
Supports: The canonical target resource for writing a generated clinical note back to a chart.
AICPA · Standard · Tier A — primary documentation
Supports: What a SOC 2 Type II report does and does not attest to during a vendor security review.
NIST speech recognition evaluation literature · Methodology · Tier B — published methodology
Supports: Why a headline WER figure without a stated corpus, audio condition and reference-transcript protocol is not comparable across vendors.
Source tiers are defined on the methodology page. Outbound links are unaffiliated and carry no commercial relationship.
Frequently asked questions
- Does Speechmatics have an API?
- Public developer API. Speech-to-text platform with strong accent and language coverage, available as cloud API or on-premises container deployment. An engineer can obtain access and make a call without a contract.
- How do you authenticate with the Speechmatics API?
- API key for cloud; licensed container for self-hosted. Transport: REST batch jobs and real-time WebSocket transcription.
- What does the Speechmatics API return?
- Transcripts with diarisation and formatting; no clinical documentation layer
- Is Speechmatics a good fit for embedding in my software?
- Products with strict data-residency or on-premise requirements, or heavy multilingual needs. Teams that want a managed clinical documentation outcome rather than an engine.
- What are Speechmatics's main limitations?
- Transcription only — no clinical note generation. Self-hosting shifts substantial operational burden to you. No healthcare-specific integration or template layer.
- How was Speechmatics scored?
- Against seven weighted criteria under rubric v1.0. Speechmatics scores 7.2 of 10 overall. Methodology.
- How much does Speechmatics disclose publicly?
- 69 of 8 disclosure checks in our Vendor Transparency Index are met by published documentation. Transparency index.