PoC: Text To Speech with VibeVoice #236
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 12 commits
December 15, 2025 10:02
- Replace stub implementation with real VibeVoice model integration - Add lazy loading of model and processor - Support device auto-detection (cuda/mps/cpu) - Implement text-to-speech generation with streaming output - Add proper audio resampling from 24kHz to 48kHz - Support configurable speaker voices - Add comprehensive test script (test_vibevoice.py) - Include error handling and fallback audio generation
- Create run_vibevoice_test.sh for easy test execution - Set up PYTHONPATH to include VibeVoice installation - Make script executable - Support all test arguments pass-through
- Handle bfloat16 tensors in audio conversion - Flatten multi-dimensional audio arrays before resampling - Add improved error handling for audio generation - Successfully generates real TTS audio from text - Audio is properly resampled from 24kHz to 48kHz for WebRTC
Generated audio from text: 'Hello, this is a test.' Duration: 2 seconds @ 48kHz Speaker: Emma (en-Emma_woman)
- Add vibevoice as git dependency from GitHub - Pin transformers to 4.51.3 for compatibility - Add hatch.metadata.allow-direct-references for git dependencies - Update voice file search to check multiple locations: 1. VIBEVOICE_VOICES_DIR environment variable 2. ~/VibeVoice/demo/voices/streaming_model 3. Installed package (if demo files included) - Remove PYTHONPATH requirement from test script - Provides better error messages when voices not found
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.