| { |
| "id": "b91265e5-1b03-4b63-8dc3-4abd9a030e08", |
| "revision": 0, |
| "last_node_id": 14, |
| "last_link_id": 44, |
| "nodes": [ |
| { |
| "id": 3, |
| "type": "SaveAudio", |
| "pos": [ |
| -1040, |
| -1130 |
| ], |
| "size": [ |
| 270, |
| 112 |
| ], |
| "flags": {}, |
| "order": 6, |
| "mode": 0, |
| "inputs": [ |
| { |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 27 |
| } |
| ], |
| "outputs": [], |
| "properties": { |
| "Node name for S&R": "SaveAudio", |
| "cnr_id": "comfy-core", |
| "ver": "0.3.52", |
| "ue_properties": { |
| "widget_ue_connectable": { |
| "filename_prefix": true, |
| "audioUI": true |
| }, |
| "version": "7.0.1" |
| } |
| }, |
| "widgets_values": [ |
| "audio/VibeVoice" |
| ] |
| }, |
| { |
| "id": 13, |
| "type": "MarkdownNote", |
| "pos": [ |
| -1898.1748046875, |
| -1409.22314453125 |
| ], |
| "size": [ |
| 1035.619873046875, |
| 211.96694946289062 |
| ], |
| "flags": {}, |
| "order": 0, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "title": "Note", |
| "properties": {}, |
| "widgets_values": [ |
| "# ComfyUI-VibeVoice\n\nVibeVoice is a novel framework by Microsoft for generating expressive, long-form, multi-speaker conversational audio. It excels at creating natural-sounding dialogue, podcasts, and more, with consistent voices for up to 4 speakers.\n\n**✨ Key Features:**\n* **Multi-Speaker TTS:** Generate conversations with up to 4 distinct voices in a single audio output.\n* **High-Fidelity Voice Cloning:** Use any audio file (`.wav`, `.mp3`) as a reference for a speaker's voice.\n* **Hybrid Generation Mode:** Mix and match cloned voices with high-quality, zero-shot generated voices in the same script.\n* **Flexible Scripting:** Use simple `[1]` tags or the classic `Speaker 1:` format to write your dialogue.\n* **Advanced Attention Mechanisms:** Choose between `eager`, `sdpa`, `flash_attention_2`, and the high-performance `sage` attention for fine-tuned control over speed and compatibility.\n* **Robust 4-Bit Quantization:** Run the large language model component in 4-bit mode to significantly reduce VRAM usage.\n* **Automatic Model Management:** Models are downloaded automatically and managed efficiently by ComfyUI to save VRAM." |
| ], |
| "color": "#233", |
| "bgcolor": "#355" |
| }, |
| { |
| "id": 4, |
| "type": "LoadAudio", |
| "pos": [ |
| -1900, |
| -1130 |
| ], |
| "size": [ |
| 272.9800720214844, |
| 136 |
| ], |
| "flags": {}, |
| "order": 1, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [ |
| { |
| "name": "AUDIO", |
| "type": "AUDIO", |
| "links": [] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "LoadAudio", |
| "cnr_id": "comfy-core", |
| "ver": "0.3.52", |
| "ue_properties": { |
| "widget_ue_connectable": { |
| "audio": true, |
| "audioUI": true, |
| "upload": true |
| }, |
| "version": "7.0.1" |
| } |
| }, |
| "widgets_values": [ |
| "male_rickmorty.mp3", |
| null, |
| null |
| ] |
| }, |
| { |
| "id": 8, |
| "type": "LoadAudio", |
| "pos": [ |
| -1901.10009765625, |
| -948.7998046875 |
| ], |
| "size": [ |
| 274.080078125, |
| 136 |
| ], |
| "flags": {}, |
| "order": 2, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [ |
| { |
| "name": "AUDIO", |
| "type": "AUDIO", |
| "links": [] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "LoadAudio", |
| "cnr_id": "comfy-core", |
| "ver": "0.3.52", |
| "ue_properties": { |
| "widget_ue_connectable": { |
| "audio": true, |
| "audioUI": true, |
| "upload": true |
| }, |
| "version": "7.0.1" |
| } |
| }, |
| "widgets_values": [ |
| "male_stewie.mp3", |
| null, |
| null |
| ] |
| }, |
| { |
| "id": 12, |
| "type": "MarkdownNote", |
| "pos": [ |
| -1915.701904296875, |
| -762.380126953125 |
| ], |
| "size": [ |
| 312.85455322265625, |
| 292.8734130859375 |
| ], |
| "flags": {}, |
| "order": 3, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "title": "Note", |
| "properties": {}, |
| "widgets_values": [ |
| "### Scripting and Voice Modes\n\n#### Speaker Tagging\nYou can assign lines to speakers in two ways. Both are treated identically.\n\n* **Modern Format (Recommended):** `[1] This is the first speaker.`\n* **Classic Format:** `Speaker 1: This is the first speaker.`\n\nYou can also add an optional colon to the modern format (e.g., `[1]: ...`). The node handles all variations consistently.\n\n#### Hybrid Voice Generation\nThis is a powerful feature that lets you mix cloned voices and generated (zero-shot) voices.\n\n* **To Clone a Voice:** Connect a `Load Audio` node to the speaker's input (e.g., `speaker_1_voice`).\n* **To Generate a Voice:** Leave the speaker's input empty. The model will create a unique, high-quality voice for that speaker." |
| ], |
| "color": "#233", |
| "bgcolor": "#355" |
| }, |
| { |
| "id": 14, |
| "type": "MarkdownNote", |
| "pos": [ |
| -1048.3660888671875, |
| -960.8771362304688 |
| ], |
| "size": [ |
| 280.797607421875, |
| 487.02728271484375 |
| ], |
| "flags": {}, |
| "order": 4, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "title": "Note", |
| "properties": {}, |
| "widgets_values": [ |
| "## Models\n\nWill be downloaded on the first run, or download them manually and place them into the directory: /models/tts/VibeVoice\n\n| Model | Context Length | Generation Length | Weight |\n|-------|----------------|----------|----------|\n| VibeVoice-1.5B | 64K | ~90 min | [HF link](https://huggingface.co/microsoft/VibeVoice-1.5B) |\n| VibeVoice-Large| 32K | ~45 min | [HF link](https://huggingface.co/microsoft/VibeVoice-Large) |\n\n## Support \n\n- Don't know how to update PyTorch?\n- Need help with ComfyUI?\n- Need technical support?\n\n### Or do you just have questions? Then join the [@TokenDiffusion Hub](https://t.me/TokenDiff_hub) group\n\n### AI news [TokenDiffusion](https://t.me/TokenDiff)" |
| ], |
| "color": "#233", |
| "bgcolor": "#355" |
| }, |
| { |
| "id": 11, |
| "type": "VibeVoiceTTS", |
| "pos": [ |
| -1570, |
| -1130 |
| ], |
| "size": [ |
| 475.3999938964844, |
| 662.9000244140625 |
| ], |
| "flags": {}, |
| "order": 5, |
| "mode": 0, |
| "inputs": [ |
| { |
| "name": "speaker_1_voice", |
| "shape": 7, |
| "type": "AUDIO", |
| "link": null |
| }, |
| { |
| "name": "speaker_2_voice", |
| "shape": 7, |
| "type": "AUDIO", |
| "link": null |
| }, |
| { |
| "name": "speaker_3_voice", |
| "shape": 7, |
| "type": "AUDIO", |
| "link": null |
| }, |
| { |
| "name": "speaker_4_voice", |
| "shape": 7, |
| "type": "AUDIO", |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "name": "AUDIO", |
| "type": "AUDIO", |
| "links": [ |
| 27 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "VibeVoiceTTS", |
| "cnr_id": "ComfyUI-VibeVoice", |
| "ver": "37803a884fb8f9b43c38286f6d654c7f97181a73", |
| "ue_properties": { |
| "widget_ue_connectable": { |
| "model_name": true, |
| "text": true, |
| "quantize_llm_4bit": true, |
| "attention_mode": true, |
| "cfg_scale": true, |
| "inference_steps": true, |
| "seed": true, |
| "do_sample": true, |
| "temperature": true, |
| "top_p": true, |
| "top_k": true |
| }, |
| "version": "7.0.1" |
| } |
| }, |
| "widgets_values": [ |
| "VibeVoice-1.5B", |
| "[1] I can't believe you did it again. I waited for two hours. Two hours! Not a single call, not a text. Do you have any idea how embarrassing that was, just sitting there alone?\n[2] Look, I know, I'm sorry, alright? Work was a complete nightmare. My boss dropped a critical deadline on me at the last minute. I didn't even have a second to breathe, let alone check my phone.\n", |
| false, |
| "flash_attention_2", |
| 1.3, |
| 10, |
| 471935335072093, |
| "fixed", |
| true, |
| 0.95, |
| 0.95, |
| 0, |
| false |
| ], |
| "color": "#232", |
| "bgcolor": "#353" |
| } |
| ], |
| "links": [ |
| [ |
| 27, |
| 11, |
| 0, |
| 3, |
| 0, |
| "AUDIO" |
| ] |
| ], |
| "groups": [], |
| "config": {}, |
| "extra": { |
| "ds": { |
| "scale": 0.8264462809917354, |
| "offset": [ |
| 2015.701904296875, |
| 1509.22314453125 |
| ] |
| }, |
| "ue_links": [], |
| "links_added_by_ue": [], |
| "frontendVersion": "1.26.11", |
| "VHS_latentpreview": false, |
| "VHS_latentpreviewrate": 0, |
| "VHS_MetadataImage": true, |
| "VHS_KeepIntermediate": true |
| }, |
| "version": 0.4 |
| } |
