TTS.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/speech-elevenlabs";
 
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/speech-openai";
 
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);

Basic Audio Generation (PlayAI)

import { PlayAITTS } from "@mastra/speech-playai";
 
const tts = new PlayAITTS({
  model: {
    name: "PlayDialog",
    apiKey: process.env.PLAYAI_API_KEY!,
  },
  userId: process.env.PLAYAI_USER_ID!,
});
 
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);

Azure Generation

import { AzureTTS } from "@mastra/speech-azure";
 
const tts = new AzureTTS({
  model: {
    name: "en-US-JennyNeural",
    apiKey: process.env.AZURE_API_KEY,
    region: process.env.AZURE_REGION,
  },
});
 
const { audioResult } = await tts.generate({ text: "What is AI?" });
await writeFile(
  path.join(process.cwd(), "/test-outputs/azure-output.mp3"),
  audioResult,
);

Deepgram Generation

import { DeepgramTTS } from "@mastra/speech-deepgram";
 
const tts = new DeepgramTTS({
  model: {
    name: "aura",
    voice: "asteria-en",
    apiKey: process.env.DEEPGRAM_API_KEY,
  },
});
 
const { audioResult } = await tts.generate({ text: "What is AI?" });
await writeFile(
  path.join(process.cwd(), "/test-outputs/deepgram-output.mp3"),
  audioResult,
);

Google Generation

import { GoogleTTS } from "@mastra/speech-google";
 
const tts = new GoogleTTS({
  model: {
    name: "en-US-Standard-A",
    credentials: process.env.GOOGLE_CREDENTIALS,
  },
});
 
const { audioResult } = await tts.generate({ text: "What is AI?" });
await writeFile(
  path.join(process.cwd(), "/test-outputs/google-output.mp3"),
  audioResult,
);

IBM Generation

import { IbmTTS } from "@mastra/speech-ibm";
 
const tts = new IbmTTS({
  model: {
    voice: "en-US_AllisonV3Voice",
    apiKey: process.env.IBM_API_KEY,
  },
});
 
const { audioResult } = await tts.generate({ text: "What is AI?" });
await writeFile(
  path.join(process.cwd(), "/test-outputs/ibm-output.mp3"),
  audioResult,
);

Murf Generation

import { MurfTTS } from "@mastra/speech-murf";
 
const tts = new MurfTTS({
  model: {
    name: "GEN2",
    voice: "en-US-natalie",
    apiKey: process.env.MURF_API_KEY,
  },
});
 
const { audioResult } = await tts.generate({ text: "What is AI?" });
await writeFile(
  path.join(process.cwd(), "/test-outputs/murf-output.mp3"),
  audioResult,
);

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

Providers and Models .stream()