Speech to Text API

API service

Speechmatics' automatic speech recognition API transcribes audio into text in 55+ languages in either real-time streaming or batch mode, with speaker diarization, custom dictionary, translation and summarization options.

Find alternatives to Speech to Text API

TypeAPI service
RoleStandalone tool
AvailabilitySold
DeploymentSaaS, Self-hosted, Hybrid
Intended forDeveloper, Enterprise
SecurityVendor-asserted
CertificationsISO/IEC 27001, SOC 2 Type II
Trains on customer dataNo
Zero data retentionUnknown
Data residencyNot recorded
Security featuresEncryption at rest
StatusActive
Sold withinSold on its own
PricingFreemium, Usage-based, Enterprise quote — official pricing ↗

What it does

Used for

Features 14

speechmatics.com

How it compares

Sources

Pricing

Pricing page · 5 Sep 2026

Description

Official documentation · 5 Sep 2026

Product page markets a Speech-to-Text API across 55+ languages, real-time and batch, sub-500ms latency, speaker diarization, alphanumeric recognition.

Used for

Official documentation · 22 Oct 2026

'Power voice assistants or AI agents with live input' (https://docs.speechmatics.com/speech-to-text.md) / 'Transcribe recorded meetings or interviews' (https://docs.speechmatics.com/speech-to-text.md) / 'Generate clinical notes at scale with Voice AI, understanding medical terminology.' (https://www.speechmatics.com/speech-to-text)

Constraints

Trust centre · 2 Oct 2026

Derived from the security facts on this page, from the same source.

Security

Trust centre · 2 Oct 2026

Platform-wide security page (cloud-hosted products; on-device STT left out). HIPAA is claimed as 'fully compliant' with no BAA stated, GDPR as 'compliant with ... directives such as the GDPR' with no DPA, so hipaa-baa and gdpr-dpa omitted. SafeBase trust centre linked from the page was not read (script portal). ZDR and specific residency regions not stated. Training is from the Terms and Conditions (s10.4): Speechmatics 'will not use Your inputs, outputs or any other data for machine learning or model training purposes unless You opt in'.

Sold within

Live re-check 2026-09-15: speechmatics.com/pricing shows Speech-to-Text as its own line with independent price tiers, no parent packaging stated.

Deployment

Official documentation · 5 Sep 2026

Lists On-Prem ('Docker containers, Kubernetes, or a preconfigured virtual appliance'), Cloud and On-Device as the deployment modes; docs.speechmatics.com/deployments documents CPU/GPU speech-to-text containers, a language-ID container and a translation container.

Interfaces

Official documentation · 12 Oct 2026

Page: 'Speech to Text API built for real-world accuracy'.

Modalities

Official documentation · 1 Oct 2026

Page: 'Our API handles live and recorded audio at scale / Transcribe your voice in real time'.

Intended for

Self-reported · 8 Sep 2026

Quickstart guides/API docs for builders; 'enterprise-grade speech-to-text', enterprise plans; case studies with Adobe, LiveKit, AI Media

Also from Speechmatics

Open Speechmatics in the directory

Something wrong here? Send a correction — quote this product id: speechmatics-speech-to-text.