`generate()`

The generate() method is used to interact with the TTS model to produce an audio response. This method accepts text and voice as parameters.

Parameters

text:

string

The messages to be processed by TTS.

voice:

string

Voice ID to be used with generation.

Returns

audioResult?:

Readable

The generated audio stream

Examples

Basic Audio Generation (ElevenLabs)

import { ElevenLabsTTS } from '@mastra/tts'
 
 const tts = new ElevenLabsTTS({
    model: {
      name: 'eleven_multilingual_v2',
      apiKey: process.env.ELEVENLABS_API_KEY!,
    },
  });
 
const voices = await tts.voices();
const voiceId = voices?.[0]?.voice_id!;
 
const { audioResult } = await tts.generate({ text: "What is AI?", voice: voiceId });
 
await writeFile(path.join(process.cwd(), '/test-outputs/generate-output.mp3'), audioBuffer);

Basic Audio Generation (OpenAI)

import { OpenAITTS } from '@mastra/tts'
 
 const tts = new OpenAITTS({
    model: {
      name: 'tts-1',
      apiKey: process.env.OPENAI_API_KEY!,
    },
  });
 
const voices = await tts.voices();
const voiceId = voices?.[0]?.voice_id!;
 
const { audioResult } = await tts.generate({ text: "What is AI?", voice: voiceId });
 
const outputPath = path.join(process.cwd(), 'test-outputs/open-aigenerate-test.mp3');
writeFileSync(outputPath, audioResult);

For streaming audio responses, see the stream() method documentation.

Providers and Models stream

generate()