homeguild_voice_openai_tts

OpenAI TTS provider for homeguild_voice_kit. Natural-sounding text-to-speech with a streaming sentence queue, voice selection, and speed control.

Part of Voice Kit by HomeGuild Labs.

Usage

import 'package:homeguild_voice_openai_tts/homeguild_voice_openai_tts.dart';

final tts = OpenAITTSProvider(
  apiKey: 'YOUR_OPENAI_KEY',
  voice: 'alloy',        // alloy, echo, fable, onyx, nova, shimmer
  speed: 1.25,            // 0.25 to 4.0
  model: 'tts-1',         // or 'tts-1-hd' for higher quality
  textSanitizer: (text) => text.replaceAll('**', ''),  // strip markdown
  onUsageTracked: (seconds) => print('Used ${seconds}s of TTS'),
);

Pass it to VoiceConversationManager from homeguild_voice_kit:

final manager = VoiceConversationManager(
  sttProvider: stt,
  ttsProvider: tts,
  streamAdapter: myBackend,
);

Features

• Streaming sentence queue with sequential playback
• Six voice options: alloy, echo, fable, onyx, nova, shimmer
• Runtime speed adjustment (0.25x to 4.0x)
• Optional text sanitizer callback (strip markdown, clean formatting)
• Optional usage tracking callback
• Graceful queue clearing for interruptions

Requirements

• An OpenAI API key with TTS access

License

MIT — see LICENSE.