TTS Providers

interface TTSProvider {
  readonly name: string;
  synthesize(text: string, options?: TTSOptions): Promise<Buffer>;
  streamSynthesize(text: string, options?: TTSOptions): AsyncGenerator<Buffer>;
}

import { OpenAITTS } from '@cogitator-ai/voice';

const tts = new OpenAITTS({
  apiKey: process.env.OPENAI_API_KEY!,
  model: 'gpt-4o-mini-tts',
  voice: 'coral',
});

const audio = await tts.synthesize('Hello, world!', {
  speed: 1.0,
  format: 'mp3',
  instructions: 'Speak in a warm, friendly tone',
});

fs.writeFileSync('output.mp3', audio);

for await (const chunk of tts.streamSynthesize('Streaming response...')) {
  playAudio(chunk);
}

await tts.synthesize('Welcome to the show!', {
  instructions: 'Speak with excitement and energy, like a TV host',
});

await tts.synthesize('I am sorry for the inconvenience.', {
  instructions: 'Speak softly with genuine empathy',
});

import { ElevenLabsTTS } from '@cogitator-ai/voice';

const tts = new ElevenLabsTTS({
  apiKey: process.env.ELEVENLABS_API_KEY!,
  model: 'eleven_flash_v2_5',
  voiceId: '21m00Tcm4TlvDq8ikWAM',
});

const audio = await tts.synthesize('Hello!', { format: 'mp3' });
fs.writeFileSync('output.mp3', audio);

for await (const chunk of tts.streamSynthesize('Streaming audio...')) {
  playAudio(chunk);
}

import type { TTSProvider, TTSOptions } from '@cogitator-ai/voice';

class PiperTTS implements TTSProvider {
  readonly name = 'piper';

  async synthesize(text: string, options?: TTSOptions): Promise<Buffer> {
    // call your local Piper instance
    return Buffer.alloc(0);
  }

  async *streamSynthesize(text: string, options?: TTSOptions): AsyncGenerator<Buffer> {
    const audio = await this.synthesize(text, options);
    yield audio;
  }
}