ComfyUI's shared Python environment creates dependency conflicts, as exemplified by Qwen3-TTS requiring transformers==4.57.3 while newer models need Transformers 5.x, causing workflows to break. The a…
Researchers are using text-to-speech systems to create synthetic training data for spoken question answering in Luxembourgish, a low-resource language. By translating existing QA resources and synthes…
A developer added opt-in GPU backends (Metal and CUDA) to a pure-C TTS inference engine for Qwen3-TTS, achieving faster-than-real-time performance on Apple Silicon and NVIDIA GPUs. The key optimizatio…
Researchers developed a spoken question answering system for Luxembourgish using text-to-speech augmentation, training a SLAM-style architecture with frozen Whisper and multilingual LLM backends. Mult…
Hugging Face and Pollen Robotics demonstrated a fully local conversational AI pipeline on the Reachy Mini desktop robot, using Silero VAD v5, Parakeet-TDT 0.6B v3, Gemma 4 or Qwen3-4B LLM, and Qwen3-T…
Alibaba's 1.7B parameter Qwen3-TTS voice cloning model was fine-tuned using Fully Sharded Data Parallel (FSDP) with PyTorch and Ray, demonstrating memory-efficient distributed training across 4 GPUs. …
The open-text-to-speech (TTS) landscape has shifted dramatically between 2024 and mid-2026, with open-weight models now rivaling proprietary APIs from ElevenLabs, Google, and OpenAI in quality while o…
Pollen Robotics and Hugging Face have released a fully local speech-to-speech pipeline for the Reachy Mini robot, eliminating the need for cloud servers or API keys. The open-source stack runs entirel…
Voicebox, an open-source AI voice studio with 28,500 GitHub stars and an MIT license, runs entirely on local hardware and combines voice cloning, dictation, and text-to-speech across 23 languages. The…
Practical advantages of using an RTX PRO 6000 Blackwell Max-Q with 96GB VRAM for complex AI agent loops, such as a voice roleplay and storyboard-to-video pipeline. The author explains that this VRAM c…