Description
Turning speech into subtitles in a ComfyUI workflow means exporting to another tool first. ComfyUI-Qwen3-ASR provides ComfyUI speech recognition nodes built on Qwen3-ASR for audio-to-text inside the workflow.
It supports 52 languages and dialects and pairs with ComfyUI-Qwen3-TTS for complete speech workflows.
Transcription:Inside workflows.
52 languages:Including dialects.
TTS pairing:Full speech pipelines.
It supports 52 languages and dialects and pairs with ComfyUI-Qwen3-TTS for complete speech workflows.
Features
Transcription:Inside workflows.
52 languages:Including dialects.
TTS pairing:Full speech pipelines.
