Azure Speech-to-Text
Audio Available Full comparison ↗ microsoft-azure/speech-stt · by Microsoft
· end-to-end-asr
Pricing — 1 offering(s)
About this offering: Azure Cognitive Services Speech-to-Text. Supports 100+ languages with automatic language detection and speaker diarisation. Tight integration with Azure services, Active Directory, and compliance frameworks (SOC 2, ISO 27001, HIPAA). Custom model training available for domain-specific terminology. Commitment pricing: ~$0.60/hr for 100 hours/month. Priced at $1.00/hour ($0.0167/min) pay-as-you-go with 5 free hours/month. Streaming and batch transcription supported. Pronunciation assessment available as an add-on feature.
Standard transcription
- $0.0167 / minute Current 2017-06-01 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how Azure Speech-to-Text fits into a cost-aware routing setup
See how →Capability profile
How Azure Speech-to-Text rates across core capability dimensions, with the task-level evidence behind each rating.
High accuracy on clean audio and well-structured speech. Custom Speech model training further improves domain-specific accuracy. Strong on formal/business speech.
100+ languages and locales. Multilingual transcription (multiple languages in the same audio) supported.
Built-in speaker diarisation. Conversation transcription endpoint is optimised for multi-speaker scenarios (meetings, calls).
WebSocket streaming via the Speech SDK. Stable and production-grade for enterprise deployments.
Custom Speech training pipeline: upload domain audio and transcripts to fine-tune models. Phrase lists available for lightweight customisation.
Benchmarks
| Benchmark | Score | Config | Source |
|---|---|---|---|
| WER (published, Microsoft Word Error Rate report) | — | — | — |
Operator guidance
Best for enterprise teams on Azure needing compliance, custom model training, and Microsoft ecosystem integration (Teams, Dynamics). At $1.00/hour ($0.0167/min) it is the most expensive major STT option but provides the strongest enterprise governance story. For cost, Universal-2 ($0.15/hr) is 6× cheaper. For streaming latency, Deepgram Nova-3 is faster.
Use cases
- Enterprise transcription within Azure-native infrastructure
- Compliance-sensitive industries (healthcare, finance) requiring HIPAA/SOC 2
- Meeting and call centre transcription with speaker diarisation
- Custom Speech model training for domain-specific terminology
Limitations
- Most expensive major STT API at $1.00/hour PAYG
- Custom Speech training requires audio dataset preparation — higher onboarding cost
- Speech SDK dependency for streaming; REST API for batch only