# Azure AI Speech (Text to Speech) — card for AI agents

Azure neural text-to-speech with HD voices, long audio and Limited Access custom voices.

Category: Voiceover (text-to-speech) · maker Microsoft · checked 2026-10-12

## Price
- Price: Free tier
- Free tier: F0: 0.5 million Neural characters free per month.
- Usage price: S1 Neural $15/1M chars; Neural HD $22/1M; Long Audio $100/1M; custom neural $24/1M + training and hosting (eastus list).
- Pricing page: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/

## License
Microsoft Product Terms (Azure Service Specific Terms, TTS Services) — https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA

- commercial: **conditions** (Commercial use with conditions)
  > For Customers of the paid tier TTS Service only, Customer may use the audio output of prebuilt neural voices generated using the TTS Service, including for commercial purposes.
  (https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA)
- in app: **conditions** (Ship inside your app with conditions)
  > For Customers of the paid tier TTS Service only, Customer may use the audio output of prebuilt neural voices generated using the TTS Service, including for commercial purposes.
  (https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA)
- youtube: **conditions** (Monetized YouTube with conditions)
  > For Customers of the paid tier TTS Service only, Customer may use the audio output of prebuilt neural voices generated using the TTS Service, including for commercial purposes.
  (https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA)

## Rules to follow
- Apply for Limited Access and submit a voice-talent consent recording before creating a custom voice.
- Disclose synthetic voice use as the transparency notes require.

## How an agent gets files
- POST https://<region>.tts.speech.microsoft.com/cognitiveservices/v1 with an SSML body and an X-Microsoft-OutputFormat header; the Speech SDK is the recommended route. (sign-in: api-key)
- Formats: mp3, opus, wav, pcm, alaw, mulaw
- Not allowed: REST audio is truncated at 10 minutes per request.
- Not allowed: Requires an Azure account and a Speech resource key.

## How to connect
- Public API
- API docs: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/ (API key needed)
- npm: `npm install microsoft-cognitiveservices-speech-sdk`
- PyPI: `pip install azure-cognitiveservices-speech`
- Website: https://azure.microsoft.com/en-us/products/ai-services/ai-speech

## Numbers (AgentGid data)
- Used in 2 public projects set up for AI coding agents

## Lines to paste into your prompt or AGENTS.md

```
- Azure AI Speech (Text to Speech) (Voiceover (text-to-speech)). Azure neural text-to-speech with HD voices, long audio and Limited Access custom voices. Price: free tier; commercial use with conditions; ship inside your app with conditions.
  Connect: API docs https://learn.microsoft.com/en-us/azure/ai-services/speech-service/ (API key needed); npm microsoft-cognitiveservices-speech-sdk; PyPI azure-cognitiveservices-speech.
  Get files: POST https://<region>.tts.speech.microsoft.com/cognitiveservices/v1 with an SSML body and an X-Microsoft-OutputFormat header; the Speech SDK is the recommended route (mp3, opus, wav, pcm, alaw, mulaw).
  Not allowed: REST audio is truncated at 10 minutes per request.
  Not allowed: Requires an Azure account and a Speech resource key.
  Rule: Apply for Limited Access and submit a voice-talent consent recording before creating a custom voice.
  Rule: Disclose synthetic voice use as the transparency notes require.
  License: https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA (checked 2026-10-12; details: https://agentgid.com/assets/azure-tts/)
```

Not verified: Prices come from the Retail Prices API (the public page shows placeholders); no commercial restriction stated.

## Links
- AgentGid page: https://agentgid.com/assets/azure-tts/
- Is it free for commercial use? https://agentgid.com/assets/azure-tts/commercial-use/
- Source: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/
- Source: https://prices.azure.com/api/retail/prices?$filter=armRegionName eq 'eastus' and contains(meterName,'Neural')
- Source: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice
- Source: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts
- Source: https://www.microsoft.com/licensing/terms/productoffering/MicrosoftAzure/MCA

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.