llamadart 本地语音链路：Qwen3-ASR + Qwen3-TTS 让游戏角色开口

mkdir -p llama-voice-demo/bin
cdllama-voice-demo
cat > pubspec.yaml <<'YAML'
name: llama_voice_demo
publish_to: none
environment:
  sdk: ^3.10.7
dependencies:
  llamadart: 0.11.0YAMLdart pub get

cat > bin/voice.dart <<'DART'
import 'dart:io';

import 'package:llamadart/llamadart.dart';

const params = ModelParams(
  contextSize: 4096,
  numberOfThreads: 4,
  numberOfThreadsBatch: 4,
);

const sources = {
  'asr': (
    'ggml-org/Qwen3-ASR-0.6B-GGUF',
    '928ab958557df9aa2ef1c93e0e83c7ad0933fae2',
  ),
  'omni': (
    'ggml-org/Qwen2.5-Omni-3B-GGUF',
    '75f1b73b657a50f5092502799457ccb4a4a1f9df',
  ),
  'dialogue': (
    'unsloth/Qwen3.5-0.8B-GGUF',
    '6ab461498e2023f6e3c1baea90a8f0fe38ab64d0',
  ),
  'tts': (
    'ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF',
    'ca27d74bc954b73dadab5b71ca265d87fc861a7c',
  ),
  'smallTts': (
    'mradermacher/Qwen3-TTS-12Hz-0.6B-Base-GGUF',
    '0762b31e9cd99274d49dca4e895bd81863134f08',
  ),
};

ModelSource model(String family, String file) {
  final (repo, revision) = sources[family]!;
  return ModelSource.huggingFace(
    repoId: repo,
    revision: revision,
    filePath: file,
  );
}

Future<void> main(List<String> args) async {
  if (args.isEmpty ||
      args.length > 3 ||
      (args.length > 1 && !['small', 'staged', 'audio'].contains(args[1]))) {
    stderr.writeln(
      'Usage: dart run bin/voice.dart question.wav '
      '[small|staged|audio] [voice-reference.wav]',
    );
    exitCode = 64;
    return;
  }
  final question = args[0];
  final small = args.length == 1 || args[1] == 'small';
  final directAudio = args.length > 1 && args[1] == 'audio';
  final reference = args.length == 3 ? args[2] : null;
  for (final path in [question, if (reference != null) reference]) {
    if (!await File(path).exists()) {
      throw ArgumentError('Audio file not found:$path');
    }
  }

  String? transcript;
  if (!directAudio) {
    final asr = await SpeechToTextEngine.load(
      SpeechToTextModel(
        model('asr', 'Qwen3-ASR-0.6B-Q8_0.gguf'),
        projector: model('asr', 'mmproj-Qwen3-ASR-0.6B-Q8_0.gguf'),
        adapter: const Qwen3AsrAdapter(),
      ),
      params: params,
    );
    try {
      final result = await asr.transcribeOnce(
        SpeechToTextRequest(
          audio: SpeechAudioFileInput(question),
          contextPrompt: 'Mo, Pip, Dash, Llama Village',
        ),
      );
      transcript = result.text.trim();
      if (transcript.isEmpty) throw StateError('No speech recognized');
      stdout.writeln('Dash:$transcript');
    } finally {
      await asr.dispose();
    }
  }

  final llm = await LlamaEngine.load(
    LlamaModel(
      small
          ? model('dialogue', 'Qwen3.5-0.8B-Q4_K_M.gguf')
          : model('omni', 'Qwen2.5-Omni-3B-Q4_K_M.gguf'),
      projector: directAudio
          ? model('omni', 'mmproj-Qwen2.5-Omni-3B-Q8_0.gguf')
          : null,
    ),
    params: params,
  );
  final reply = StringBuffer();
  try {
    if (directAudio && !(await llm.capabilities).supportsAudio) {
      throw StateError('此模型/运行时无法接受音频');
    }
    await for (final chunk in llm.create(
      [
        const LlamaChatMessage.fromText(
          role: LlamaChatRole.system,
          text:
              '你是 Mo，一只友好的面包师羊驼。Dash 正在拜访你。'
              "已知事实：Pip 的红围巾在池塘边的芦苇丛里。"
              '用一句简短的英文回答访客。'
              '不要舞台提示。不要编造你不知道的事实。',
        ),
        if (transcript != null)
          LlamaChatMessage.fromText(role: LlamaChatRole.user, text: transcript)
        else
          LlamaChatMessage.withContent(
            role: LlamaChatRole.user,
            content: [LlamaAudioContent(path: question)],
          ),
      ],
      enableThinking: false,
      params: const GenerationParams(maxTokens: 100, temp: 0, seed: 42),
    )) {
      reply.write(chunk.text);
    }
  } finally {
    await llm.dispose();
  }

  final text = reply.toString().trim();
  if (text.isEmpty) throw StateError('模型没有返回回复');
  stdout.writeln('Mo:$text');
  final tts = await TextToSpeechEngine.load(
    TextToSpeechModel(
      small
          ? model('smallTts', 'Qwen3-TTS-12Hz-0.6B-Base.Q4_K_M.gguf')
          : model('tts', 'Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf'),
      projector: small
          ? model('smallTts', 'Qwen3-TTS-12Hz-0.6B-Base.mmproj-Q8_0.gguf')
          : model('tts', 'mmproj-Qwen3-TTS-12Hz-1.7B-Base-Q8_0.gguf'),
      adapter: const Qwen3TtsAdapter(),
    ),
    params: params,
  );
  try {
    final audio = await tts.synthesizeOnce(
      TextToSpeechRequest(
        text: text,
        language: 'en',
        seed: 42,
        speakerReference: reference == null
            ? null
            : SpeechAudioFileInput(reference),
      ),
    );
    await File('reply.wav').writeAsBytes(audio.toWavBytes());
    stdout.writeln('Saved reply.wav');
  } finally {
    await tts.dispose();
  }
}DART

say -o question.aiff "Mo，你见过 Pip 的红围巾吗？"
afconvert -f WAVE -d LEI16@16000 -c 1 question.aiff question.wav
dart run bin/voice.dart question.wav small
afplay reply.wav

// ASR：录音变成文本。
final result = await asr.transcribeOnce(
  SpeechToTextRequest(
    audio: SpeechAudioFileInput(question),
    contextPrompt: 'Mo, Pip, Dash, Llama Village'，
  ),
);

// TTS：生成的回答变成 WAV 文件。
final audio = await tts.synthesizeOnce(
  TextToSpeechRequest(text: text， language: 'en'， seed: 42),
);
await File('reply.wav').writeAsBytes(audio.toWavBytes()));

dart run bin/voice.dart question.wav audio
afplay reply.wav

dart run bin/voice.dart question.wav small mo-reference.wav
afplay reply.wav