Azure AI Speech (speech-to-text) by Microsoft
Transcribe audio in real time, in batch or via fast transcription, with optional custom speech models.
Speech-to-text and transcription Official MCP server
＋ Build a stack with Azure AI Speech (speech-to-text) Website Official pricing GitHub
Price
Free plan
then from $0.18 per hour
Free tier
Yes
Real-time Transcription: 5 audio hours free per month
SDK downloads
—
npm microsoft-cognitiveservices-speech-sdk · PyPI azure-cognitiveservices-speech
Pricing
| Free tier | Real-time Transcription: 5 audio hours free per month |
|---|---|
| Cheapest paid plan | — |
| Usage price | Standard: real-time $1.00 per hour, batch $0.18 per hour, fast transcription $0.36 per hour; custom real-time $1.20 per hour (East US) |
| Good to know | Free hours are shared between standard and custom; batch not supported on free tier. Pricing page loads prices dynamically; figures are from Microsoft's Azure Retail Prices API (prices.azure.com), East US. Commitment tiers available. |
From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.
Use it from an agent
| MCP server | Official: @azure/mcp |
|---|---|
| npm | npm install microsoft-cognitiveservices-speech-sdk |
| PyPI | pip install azure-cognitiveservices-speech |
Alternatives to Azure AI Speech (speech-to-text)
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| ElevenLabs Text-to-speech, speech-to-text (Scribe), voice cloning and conversational voice-agent APIs. |
Free plan: 10,000 TTS characters/month (v4) | Free plan · paid from $6/mo | 3.2M | 3,135 | MCP |
| Deepgram Real-time and batch speech-to-text, text-to-speech and voice-agent APIs. |
$200 credit, no credit card | Free plan then Nova-3 streaming $0.0048/min (promo; regular $0.0077);... |
1.7M | 469 | MCP |
| AssemblyAI Speech-to-text API (batch and streaming) with diarization, speech understanding and voice agents. |
Up to 185 hours pre-recorded and 333 hours... | Free plan then Universal-2 $0.15/hour; Universal-3.5 Pro $0.21/hour;... |
1.3M | 213 | MCP |
| Cartesia Low-latency text-to-speech (Sonic), speech-to-text (Ink) and managed voice agents. |
20K credits/month + $1 prepaid for agents | Free plan · paid from $5/mo | 286K | 134 | MCP |
| Gladia Multilingual speech-to-text API with real-time and async transcription. |
50€ in free credits (one-time, ~80+ hours... | Free plan then Async at $0.61/hr, Real-time at $0.75/hr (Starter);... |
— | — | |
| Groq Speech-to-Text (Whisper) Hosted Whisper Large V3 and V3 Turbo transcription and translation, billed per hour of audio. |
Free tier with rate limits (25 MB files) | Free plan then Whisper Large V3 Turbo $0.04/hour; Whisper Large V3... |
— | — |