mirror of
https://github.com/mastra-ai/mastra.git
synced 2026-11-17 08:44:46 +00:00
|
History
|
||
|---|---|---|
| .. | ||
| src | ||
| architecture-llm.md | ||
| CHANGELOG.md | ||
| lint-staged.config.js | ||
| package.json | ||
| README.md | ||
| tsconfig.build.json | ||
| tsconfig.json | ||
| tsdown.config.ts | ||
| vitest.config.ts | ||
@mastra/voice-azure
Add text-to-speech and speech-to-text to Mastra with Azure Speech Services, configurable voices, audio formats, transcription, and credentials.
Installation
npm install @mastra/voice-azure
Usage
import { AzureVoice } from '@mastra/voice-azure';
// Create voice with both speech and listening capabilities
const voice = new AzureVoice({
speechModel: {
apiKey: 'your-api-key', // Optional, can use AZURE_API_KEY env var
region: 'your-region', // Optional, can use AZURE_REGION env var
voiceName: 'en-US-AriaNeural', // Optional, default voice
},
listeningModel: {
apiKey: 'your-api-key', // Optional, can use AZURE_API_KEY env var
region: 'your-region', // Optional, can use AZURE_REGION env var
language: 'en-US', // Optional, recognition language
},
});
// List available voices
const voices = await voice.getSpeakers();
// Generate speech
const audioStream = await voice.speak('Hello from Mastra!', {
speaker: 'en-US-JennyNeural', // Optional: override default voice
});
// Convert speech to text
const text = await voice.listen(audioStream);
Documentation
Changelog
See the package changelog for version history and release notes.
Support
We have an open community Discord. Come and say hello and let us know if you have any questions or need any help getting things running.