feat: add VoxCPM TTS engine and update router

[phonk2682]

PR Description

This PR implements the VoxCPM TTS (Text-to-Speech) engine specifically aimed at providing high-quality, tokenizer-free speech synthesis with voice cloning capabilities.

Key changes include:

• New Engine Implementation: Added VoxCPMEngine in app/engines/tts/voxcpm/ implementing the BaseTTSEngine interface. Supports both batch synthesis and streaming (with low latency).
• Router Upgrade: Updated app/api/routers/tts.py from a placeholder stub to a fully functional router that supports:
  • POST /synthesize: Returns base64 encoded WAV audio.
  • POST /synthesize/stream: Server-Sent Events (SSE) streaming of audio chunks.
  • Request validation and error handling.
• Configuration: Registered voxcpm in engines.yaml and added necessary dependencies (voxcpm, torchcodec for cloning) to pyproject.toml.
• Testing:
  • Added comprehensive unit tests for VoxCPMEngine covering lifecycle, synthesis, streaming, and error edges (Achieved 100% coverage in app/engines/tts/voxcpm/engine.py).
  • Updated test_tts_router.py to test the actual router logic instead of expecting 501 errors, aligning test_tts_router.py coverage to 100%.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• New Engine (STT/TTS provider)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Refactor (non-breaking code cleanup or optimization)
• Documentation update
• Performance improvement

Checklist

• I have read the CONTRIBUTING guide
• My code follows the project's code style (make format)
• Linting passes (make lint)
• Tests pass (make test)
• Documentation updated (if needed)
• No sensitive information (API keys, secrets) included

Related Issues

Closes #

Testing & Verification

Automated Tests

• Unit tests added/updated
• All existing tests pass

Manual Verification (if applicable)

Verified that unit tests cover all critical paths including:

• Standard text synthesis.
• Streaming synthesis (chunk generation).
• Mocked voice cloning (prompt file handling).
• Error handling for initialization and runtime failures.

API Endpoints Tested (if applicable)

• Batch endpoint (POST /api/v1/stt/transcribe or /tts/synthesize)
• SSE streaming (POST .../stream)
• WebSocket (WS .../ws)

Engine-Specific Tests (if applicable)

• Engine type: TTS
• Provider: VoxCPM (OpenBMB)
• Model: openbmb/VoxCPM-0.5B

Security Impact

• No security implications
• Security impact (please describe below)