Refactor/api input

[minhsaco99]

Description

Refactor TTS/STT API to use form data instead of query parameters for better REST
design and file upload support. Add voice cloning capability to TTS API with
reference_audio file upload and reference_text parameters.

Key changes:

• Move text and engine_params from query params to form data (multipart/form-data)
• Add reference_audio (file) and reference_text params for voice cloning
• Update BaseTTSEngine interface with explicit voice cloning parameters
• Add temp_audio_file() context manager utility for engines requiring file paths

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)

N/A

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
• Model: N/A
• Device tested: cpu

Security Impact

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