| { |
| "id": "bd5b6a45-1b15-46f8-bac7-896bddb71347", |
| "revision": 0, |
| "last_node_id": 6, |
| "last_link_id": 4, |
| "nodes": [ |
| { |
| "id": 1, |
| "type": "MarkdownNote", |
| "pos": [ |
| 20, |
| 20 |
| ], |
| "size": [ |
| 560, |
| 520 |
| ], |
| "flags": {}, |
| "order": 0, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "properties": {}, |
| "widgets_values": [ |
| "## OGG TTS · text to speech (no reference voice)\n\n**Files**\n\n| File | Folder |\n|---|---|\n| ogg_tts.safetensors (FashionFlora/ogg-tts `model.safetensors`, renamed, about 3 GB) | models/diffusion_models |\n| drama3_codec.safetensors (the Fish codec, 1.6 GB) | models/vae |\n\nGet them from [FashionFlora/ogg-tts](https://huggingface.co/FashionFlora/ogg-tts) and [Drama-3-ComfyUI](https://huggingface.co/PedroMarinhoDev/Drama-3-ComfyUI) (the codec only). OmniVoice's config.json and tokenizer files are read from the pack's own `omnivoice` folder and fetched there on first use.\n\n**How to use:** write the text in **OGG TTS Generate**, one line per take: each line hears the two lines before and after it as context. Emotion and vocal tags go inline, e.g. [sighing], [whispering], [excited], [pause] (the node's description lists all 24). Pick the language; there are 8: en, pl, es, de, ru, fr, pt, it.\n\n**Settings:** cfg 1-1.5 keeps the natural tempo, 2 speaks faster and more pointedly. Without a reference voice a take varies with the seed: queue again for another.\n\n**Longer takes:** OGG is still training; this is a preview release, so expect some takes to be better than others." |
| ] |
| }, |
| { |
| "id": 2, |
| "type": "OggLoader", |
| "pos": [ |
| 620, |
| 20 |
| ], |
| "size": [ |
| 360, |
| 82 |
| ], |
| "flags": {}, |
| "order": 1, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "model_name", |
| "name": "model_name", |
| "type": "COMBO", |
| "widget": { |
| "name": "model_name" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "dtype", |
| "name": "dtype", |
| "type": "COMBO", |
| "widget": { |
| "name": "dtype" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_MODEL", |
| "name": "OGG_MODEL", |
| "type": "OGG_MODEL", |
| "links": [ |
| 1 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggLoader" |
| }, |
| "widgets_values": [ |
| "ogg_tts.safetensors", |
| "float32" |
| ] |
| }, |
| { |
| "id": 3, |
| "type": "OggCodecLoader", |
| "pos": [ |
| 620, |
| 160 |
| ], |
| "size": [ |
| 360, |
| 58 |
| ], |
| "flags": {}, |
| "order": 2, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codec_name", |
| "name": "codec_name", |
| "type": "COMBO", |
| "widget": { |
| "name": "codec_name" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_CODEC", |
| "name": "OGG_CODEC", |
| "type": "OGG_CODEC", |
| "links": [ |
| 2 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggCodecLoader" |
| }, |
| "widgets_values": [ |
| "drama3_codec.safetensors" |
| ] |
| }, |
| { |
| "id": 4, |
| "type": "OggGenerate", |
| "pos": [ |
| 1020, |
| 20 |
| ], |
| "size": [ |
| 400, |
| 330 |
| ], |
| "flags": {}, |
| "order": 3, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "model", |
| "name": "model", |
| "type": "OGG_MODEL", |
| "link": 1 |
| }, |
| { |
| "localized_name": "text", |
| "name": "text", |
| "type": "STRING", |
| "widget": { |
| "name": "text" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "language", |
| "name": "language", |
| "type": "COMBO", |
| "widget": { |
| "name": "language" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "seed", |
| "name": "seed", |
| "type": "INT", |
| "widget": { |
| "name": "seed" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "steps", |
| "name": "steps", |
| "type": "INT", |
| "widget": { |
| "name": "steps" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "cfg", |
| "name": "cfg", |
| "type": "FLOAT", |
| "widget": { |
| "name": "cfg" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "temperature", |
| "name": "temperature", |
| "type": "FLOAT", |
| "widget": { |
| "name": "temperature" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "split_lines", |
| "name": "split_lines", |
| "type": "BOOLEAN", |
| "widget": { |
| "name": "split_lines" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "max_frames", |
| "name": "max_frames", |
| "type": "INT", |
| "widget": { |
| "name": "max_frames" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker", |
| "name": "speaker", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "quality", |
| "name": "quality", |
| "type": "STRING", |
| "widget": { |
| "name": "quality" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "mtp_temperature", |
| "name": "mtp_temperature", |
| "type": "FLOAT", |
| "widget": { |
| "name": "mtp_temperature" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "mtp_top_k", |
| "name": "mtp_top_k", |
| "type": "INT", |
| "widget": { |
| "name": "mtp_top_k" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "mtp_rounds", |
| "name": "mtp_rounds", |
| "type": "INT", |
| "widget": { |
| "name": "mtp_rounds" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "voice", |
| "name": "voice", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_CODES", |
| "name": "OGG_CODES", |
| "type": "OGG_CODES", |
| "links": [ |
| 3 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggGenerate" |
| }, |
| "widgets_values": [ |
| "[excited] Hello! I am OGG, a text to speech model.\n[sighing] It has been a long day.\n[whispering] But I am glad you are here.", |
| "en", |
| 1, |
| "randomize", |
| 6, |
| 1.5, |
| 0.8, |
| true, |
| 0, |
| "", |
| "", |
| 0, |
| 0, |
| 4 |
| ] |
| }, |
| { |
| "id": 5, |
| "type": "OggDecode", |
| "pos": [ |
| 1460, |
| 20 |
| ], |
| "size": [ |
| 260, |
| 78 |
| ], |
| "flags": {}, |
| "order": 4, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codec", |
| "name": "codec", |
| "type": "OGG_CODEC", |
| "link": 2 |
| }, |
| { |
| "localized_name": "codes", |
| "name": "codes", |
| "type": "OGG_CODES", |
| "link": 3 |
| }, |
| { |
| "localized_name": "shorten_long_pauses", |
| "name": "shorten_long_pauses", |
| "type": "BOOLEAN", |
| "widget": { |
| "name": "shorten_long_pauses" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "AUDIO", |
| "name": "AUDIO", |
| "type": "AUDIO", |
| "links": [ |
| 4 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggDecode" |
| }, |
| "widgets_values": [ |
| false |
| ] |
| }, |
| { |
| "id": 6, |
| "type": "SaveAudio", |
| "pos": [ |
| 1460, |
| 140 |
| ], |
| "size": [ |
| 360, |
| 112 |
| ], |
| "flags": {}, |
| "order": 5, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 4 |
| }, |
| { |
| "localized_name": "filename_prefix", |
| "name": "filename_prefix", |
| "type": "STRING", |
| "widget": { |
| "name": "filename_prefix" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "audioUI", |
| "name": "audioUI", |
| "type": "AUDIO_UI", |
| "widget": { |
| "name": "audioUI" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "links": null |
| } |
| ], |
| "properties": {}, |
| "widgets_values": [ |
| "ogg/ogg_tts" |
| ] |
| } |
| ], |
| "links": [ |
| [ |
| 1, |
| 2, |
| 0, |
| 4, |
| 0, |
| "OGG_MODEL" |
| ], |
| [ |
| 2, |
| 3, |
| 0, |
| 5, |
| 0, |
| "OGG_CODEC" |
| ], |
| [ |
| 3, |
| 4, |
| 0, |
| 5, |
| 1, |
| "OGG_CODES" |
| ], |
| [ |
| 4, |
| 5, |
| 0, |
| 6, |
| 0, |
| "AUDIO" |
| ] |
| ], |
| "groups": [], |
| "config": {}, |
| "extra": { |
| "ds": { |
| "scale": 0.75, |
| "offset": [ |
| 0, |
| 0 |
| ] |
| } |
| }, |
| "version": 0.4 |
| } |
