VibeVoice · Issues· 195 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #428
VibeVoice-ASR-7B Playground "No interface is running right now"
Updated Sep 16, 2026 - #115
training on a new language
Updated Sep 3, 2026 - #402
pip install -e . failed
Updated Aug 29, 2026 - #433
Verify evals on Papers with Code
Updated Aug 28, 2026 - #432
The LLM layer of VibeVoice-powered voice agents — offering an end-to-end latency/cost breakdown across model tiers
Updated Aug 26, 2026 - #431
123456
Updated Aug 18, 2026 - #425
中国人声音
Updated Jul 30, 2026 - #400
Feature: Add SenseVoice/FunASR as an alternative STT backend
Updated Jul 14, 2026 - #332
Token indices sequence length is longer than the specified maximum sequence length for this model (153482 > 131072). Running this sequence through the model will result in indexing errors
Updated Jul 14, 2026 - #416
Audio.cpp: Optimized VibeVoice impl in C++/ggml. Generate 90-min podcast in 22.95 min, 4.08x real-time, 2.86x Python on CUDA
Updated Jun 30, 2026 - #373
VibeVoice-ASR (4-bit MLX) decoder degenerates into infinite "Yes. Yes." loop on a 36-min recording
Updated Jun 30, 2026 - #415
Encountered a bug where the content keeps repeating during transcription
Updated Jun 29, 2026 - #361
Seems that the windows and macOS clients are no longer available
Updated Jun 28, 2026 - #414
Text-Only Inference Report for Upstream
Updated Jun 23, 2026 - #407
Speaker diarization collapses on tiny waveform changes (e.g. +0.7 dB linear gain)
Updated Jun 15, 2026