Speech to Text API
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
What it does
- Speech to text
- Translation
- Summarization
- Data analysis
Used for
- Voice agent
- Meeting notes
- Clinical documentation
Features 14
- Speaker diarizationSeparates and tracks multiple speakers, including in overlapping conversations.
- Custom DictionaryInject up to 1,000 domain-specific terms for names, jargon, acronyms and branded terms.
- Real-time and batch processingStream live audio or upload files in bulk.
- Bilingual & multilingual supportBilingual models built to handle code-switching conversations without losing accuracy.
- Alphanumeric accuracyCaptures phone numbers, postcodes, account numbers and reference codes as spoken.
- Speaker identificationTags speakers consistently across separate recordings using speaker identifiers.
- Language identificationDetects the predominant language spoken in the audio and transcribes using the matching language.
- Audio eventsDetects and labels non-speech sounds in audio and video, such as music, laughter and applause.
- Audio filteringPre-processes input audio to remove low-volume background speech so it is not transcribed.
- Sentiment analysisAssesses the sentiment of what was spoken in the audio.
- Topic detectionDetects the topics discussed in the audio.
- ChaptersIdentifies distinct, continuous chapters within the audio.
- AlignmentTakes an audio file and a text file and returns the speech timing information for the text.
- End of utterance detectionDetects when a person has finished speaking in real-time transcription.
How it compares
-
Deepgram Speech-to-Text
Deepgram Alternative: Better Accuracy, 55+ Languages, Lower Cost | Speechmatics
Official documentation · 19 Sep 2026 -
AssemblyAI Pre-recorded Speech-to-Text API
Speechmatics' own comparison page is titled as a head-to-head with AssemblyAI.
Speechmatics vs AssemblyAI: Speech-to-Text Comparison (2026)
Company disclosure · 23 Sep 2026 -
Amazon Transcribe
Choose from live radio, your own voice, or sample audio to see side-by-side comparisons of Speechmatics vs Amazon Transcribe.
Official documentation · 13 Oct 2026 -
Cloud Speech-to-Text
Speechmatics delivers industry-leading accuracy on noisy, accented, real-world audio, plus deployment flexibility — on-premises, on-device, and air-gapped — that Google Cloud Speech-to-Text can't match.
Official documentation · 13 Oct 2026 -
Azure Speech in Foundry Tools
Choose from live radio, your own voice, or sample audio to see side-by-side comparisons of Speechmatics vs Azure Speech.
Official documentation · 13 Oct 2026 -
Scribe
Choose from live radio, your own voice, or sample audio to see side-by-side comparisons of Speechmatics vs ElevenLabs Scribe.
Official documentation · 13 Oct 2026 -
OpenAI API
Speechmatics delivers production-ready speech-to-text with real-time streaming, built-in speaker diarisation, and enterprise deployment — on-premises, on-device, and air-gapped — that OpenAI's transcription API cannot match.
Official documentation · 13 Oct 2026
Sources
- Pricing
- 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
-
Derived from the security facts on this page, from the same source.
- Security
-
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
-
Quickstart guides/API docs for builders; 'enterprise-grade speech-to-text', enterprise plans; case studies with Adobe, LiveKit, AI Media
Also from Speechmatics
-
Text to Speech API service
Speechmatics' text-to-speech API generates streaming synthetic English speech from text with sub-150ms latency using four named voices (Sarah, Theo, Megan, Jack), aimed at real-time voice agent use.
-
Agent STT API service
Agent STT, Speechmatics' speech-to-text API for AI voice agents: final transcripts in 350ms, speaker focus and diarization, a custom dictionary and 55+ languages, with LiveKit, Pipecat and Vapi integrations.
-
On-Device Speech to Text Developer tool
A locally-executing speech-to-text engine for Mac and Windows laptops that runs on about one CPU core plus the device's neural engine or GPU and roughly 800MB of memory, sending no audio over a network and claiming accuracy within 5% of the cloud API.
-
Translation API service
Translates a transcript into other languages in the same API call that produces it, for files or live audio. It is a feature switched on inside a Speech to Text request rather than a separate product; the docs file it under Speech to Text and return the translations alongside the transcript.
-
Summarization API service
Generates a short summary of an audio file in the same API call that transcribes it, as paragraphs or bullets. It is a Speech Intelligence feature enabled by adding a config block to a batch Speech to Text job, not a product bought on its own.
Open Speechmatics in the directory
Something wrong here? Send a correction — quote this product id: speechmatics-speech-to-text.