ComfyUI Node
Subtitle (QwenASR)
A ComfyUI node in 🧪AILab/🎙️QwenASR with 15 inputs and 4 outputs.
Subtitle (QwenASR)
- audio
- TEXT
- SUBTITLES
- LANUGAGE
- OUTPUT_PATH
â—„modelQwen/Qwen3-ASR-0.6Bâ–ş
â—„precisionbf16â–ş
â—„attentionautoâ–ş
â—„forced_alignerQwen/Qwen3-ForcedAligner-0.6Bâ–ş
â—„languageautoâ–ş
â—„hintsâ–ş
â—„output_formatnoneâ–ş
â—„output_pathâ–ş
â—„split_modesplit_by_punctuation_or_pause_or_lengthâ–ş
â—„max_gap_sec0.6â–ş
â—„max_chars40â–ş
â—„max_inference_batch_size32â–ş
â—„max_new_tokens256â–ş
â—„unload_modelstrueâ–ş
Category🧪AILab/🎙️QwenASR
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | Audio input to transcribe. | |
| modelopt | COMBO | Qwen/Qwen3-ASR-0.6B | Choose the ASR model size. |
| precisionopt | COMBO | bf16 | Inference precision. |
| attentionopt | COMBO | auto | Attention backend override. |
| forced_aligneropt | COMBO | Qwen/Qwen3-ForcedAligner-0.6B | Forced aligner for timestamped subtitles. |
| languageopt | COMBO | auto | Force language or auto-detect. |
| hintsopt | STRING | Optional hints/keywords (names, terms) to improve recognition. | |
| output_formatopt | COMBO | none | File save format only (does not change subtitle output). |
| output_pathopt | STRING | Optional output file path (relative goes to ComfyUI output). | |
| split_modeopt | COMBO | split_by_punctuation_or_pause_or_length | Sentence splitting strategy. |
| max_gap_secopt | FLOAT | 0.60–8 | Max silence gap to keep the same sentence. |
| max_charsopt | INT | 400–200 | Optional max characters per line (0 = no limit). |
| max_inference_batch_sizeopt | INT | 321–256 | Batch size for inference/alignment to avoid OOM. |
| max_new_tokensopt | INT | 2561–2048 | Max new tokens per chunk. |
| unload_modelsopt | BOOLEAN | true | Unload cached model after inference. |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| TEXT | STRING | — |
| SUBTITLES | STRING | — |
| LANUGAGE | STRING | — |
| OUTPUT_PATH | STRING | — |