feat: add OpenAI-compatible Audio Speech API endpoint

[pinghe]

Summary

• Add OpenAI-compatible POST /v1/audio/speech endpoint for TTS
• Fix torchaudio SoX backend segfault- Fix voice preset mappings referencing non-existent audio files- Enable GPU inference (was hardcoded to CPU)- Add timestamps to uvicorn access logs

Changes

New file: openai_audio_api.py

• OpenAI /v1/audio/speech request/response models (SpeechRequest, make_error_response)
• Voice mapping: OpenAI voice names to MOSS-TTS-Nano presets (alloy to Junhao, echo to Xiaoyu, etc.)
• Audio format helpers: WAV header construction, PCM 16-bit encoding, MP3 encoding via lameenc
• Streaming generators: iter_pcm_audio, generate_wav_stream, generate_mp3_stream, generate_pcm_stream
• Supports wav, mp3, and pcm response formats

app.py

• Add OpenAI-compatible endpoint using background thread + queue streaming model
  • Avoids holding _cpu_execution_lock inside ASGI streaming iterator (prevents deadlock on client disconnect)
  • _put() has 30s deadline to prevent threads from blocking indefinitely when client disconnects
  • Explicit events_gen.close() to release the lock promptly
  • Wrap lameenc return values in bytes() to fix Starlette bytearray type error
• Add _patch_torchaudio_backend(): monkey-patch torchaudio to default to soundfile backend, working around SoX segfault
• Change --device default from cpu to auto, add cuda option, use resolve_device() for auto GPU detection
• Customize uvicorn log config to add timestamps to access logs
• Add request/complete logging with elapsed time and audio chunk count

app_onnx.py, infer.py

• Add _patch_torchaudio_backend() to fix SoX segfault

moss_tts_nano_runtime.py

• Remove 8 voice presets whose audio files don't exist in the repository (Zhiming, Weiguo, Trump, Nathan, Sakura, Aoi, Hina, Mei), keeping only the 8 with actual files

pyproject.toml, requirements.txt

• Add lameenc>=1.7.0 dependency (MP3 encoding)
• Add openai_audio_api module declaration

Test plan

• WAV format returns valid audio (RIFF PCM 16-bit stereo 48kHz)
• MP3 format returns valid audio (MPEG layer III, 128kbps, 48kHz), plays correctly in mpv
• PCM format returns valid raw audio data
• Consecutive requests don't deadlock (lock released correctly)
• Service recovers after client disconnect (_put deadline mechanism)
• Invalid voice/params return OpenAI-format error JSON (HTTP 400)
• GPU auto-detection works when CUDA is available