feat: 新增音频格式与采样率配置，完善OpenAI兼容格式映射

1. 新增BYTEDANCE_TTS_FORMAT和BYTEDANCE_TTS_SAMPLE_RATE环境变量配置 2. 实现OpenAI TTS格式到火山API格式的映射转换 3. 自动处理wav格式：内部用pcm请求后封装标准WAV头 4. 动态设置响应Content-Type，适配不同输出格式 5. 更新文档与配置示例，完善日志与错误处理
2026-06-27 23:28:35 +08:00
parent 82cc68e7ee
commit 21b86bfcfe
7 changed files with 269 additions and 82 deletions
@@ -9,6 +9,8 @@ services:
      - BYTEDANCE_TTS_RESOURCE_ID=${BYTEDANCE_TTS_RESOURCE_ID}
      - BYTEDANCE_TTS_SPEAKER=${BYTEDANCE_TTS_SPEAKER}
      - BYTEDANCE_TTS_TIMEOUT=${BYTEDANCE_TTS_TIMEOUT:-30s}
+      - BYTEDANCE_TTS_FORMAT=${BYTEDANCE_TTS_FORMAT:-mp3}
+      - BYTEDANCE_TTS_SAMPLE_RATE=${BYTEDANCE_TTS_SAMPLE_RATE:-24000}
      - OPENAI_TTS_API_KEY=${OPENAI_TTS_API_KEY:-}
      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-}
      - PORT=8080