ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

MLX Local Serving (MLS) - Unified ASR, TTS, and Translation on Apple Silicon

ComfyUI nodes for Qwen3-ASR (0.6B/1.7B) and ForcedAligner. Supports high-accuracy ASR and language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features word-level timestamps, long audio transcription, and VRAM-optimized inference.

On-device voice transcription, grammar correction, and text-to-speech for macOS. Runs on MLX.

Real-time speech-to-text WebSocket server with pluggable ASR backends, energy-based VAD, streaming partial results, and Prometheus observability.

Pure-Rust inference engine for Qwen3-ASR speech recognition models (0.6B & 1.7B) using candle with Metal/CUDA acceleration

🎤 Transcribe audio to text seamlessly with ComfyUI-Qwen3-ASR, supporting 52 languages and dialects for accurate and efficient speech recognition.

Easily convert speech to timed SRT subtitles and translated captions (Colab-ready)

Qwen3-ASR Serverless Worker for RunPod

🎙️ Implement fast, dependency-free C inference for Qwen3-ASR speech-to-text models with efficient streaming on modest hardware.

Qwen3 ASR Notes