speechsdk_dev

https://speechsdk.dev/docs
Admin
Documentation repository created by Site2MD.
Tokens:1,547
Snippets:18
Trust Score:5
Update:4 months ago
Show doc for...
Tokens:
Raw
### Generate Speech with ElevenLabs v3

Source: https://speechsdk.dev

Generates speech using the ElevenLabs v3 model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'elevenlabs/eleven_v3',
  text: 'Hello from SpeechSDK!',
  voice: 'EXAVITQu4vr4xnSDxMaL',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/mpeg"
```

--------------------------------

### Generate Speech with OpenAI GPT-4o mini TTS

Source: https://speechsdk.dev

Generates speech using the OpenAI GPT-4o mini TTS model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'openai/gpt-4o-mini-tts',
  text: 'Hello from SpeechSDK!',
  voice: 'alloy',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/mpeg"
```

--------------------------------

### Generate Speech with Xai Grok-TTS

Source: https://speechsdk.dev

Generates speech using the Xai Grok-TTS model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'xai/grok-tts',
  text: 'Hello from SpeechSDK!',
  voice: 'ava',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/mpeg"
```

--------------------------------

### Generate Speech with Cartesia Sonic-3

Source: https://speechsdk.dev

Generates speech using the Cartesia Sonic-3 model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'cartesia/sonic-3',
  text: 'Hello from SpeechSDK!',
  voice: 'a0e99841-438c-4a64-b679-ae501e7d6091',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/mpeg"
```

--------------------------------

### Generate Speech with Inworld TTS 1.5 Max

Source: https://speechsdk.dev

Generates speech using the Inworld TTS 1.5 Max model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'inworld/inworld-tts-1.5-max',
  text: 'Hello from SpeechSDK!',
  voice: 'Ashley',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/mpeg"
```

--------------------------------

### Generate Speech with Google Gemini Flash TTS

Source: https://speechsdk.dev

Generates speech using the Google Gemini 3.1 Flash TTS model. Requires the '@speech-sdk/core' package.

```javascript
import { generateSpeech } from '@speech-sdk/core';

const result = await generateSpeech({
  model: 'google/gemini-3.1-flash-tts-preview',
  text: 'Hello from SpeechSDK!',
  voice: 'Kore',
});

result.audio.uint8Array;  // Uint8Array
result.audio.base64;      // string (lazy)
result.audio.mediaType;   // "audio/wav"
```

--------------------------------

### Generate Multi-Speaker Conversation

Source: https://speechsdk.dev

Generates a conversation with multiple speakers using different models and voices in a single API call. Handles automatic volume leveling and turn stitching. Requires the '@speech-sdk/core' package.

```javascript
import { generateConversation } from "@speech-sdk/core";

const result = await generateConversation({
  turns: [
    {
      model: "elevenlabs/eleven_v3",
      voice: "EXAVITQu4vr4xnSDxMaL",
      text: "Hello from the SDK.",
    },
    {
      model: "google/gemini-3.1-flash-tts-preview",
      voice: "Kore",
      text: "One call. Multiple voices. Auto-leveled.",
    },
  ],
});

result.audio.uint8Array; // Uint8Array
result.audio.mediaType;  // "audio/mpeg"
```
Tokens:
Raw