{ "id": "7129bdc4-3e2e-4f07-b73c-f3fce02e1e10", "revision": 0, "last_node_id": 11, "last_link_id": 11, "nodes": [ { "id": 1, "type": "MarkdownNote", "pos": [ 20, 20 ], "size": [ 560, 660 ], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [], "properties": {}, "widgets_values": [ "## OGG TTS ยท voice cloning\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| qwen3_asr_1.7b_bf16.safetensors (4.1 GB)
or qwen3_asr_0.6b_bf16.safetensors (1.6 GB) | models/asr |\n\nGet them from [FashionFlora/ogg-tts](https://huggingface.co/FashionFlora/ogg-tts), [Drama-3-ComfyUI](https://huggingface.co/PedroMarinhoDev/Drama-3-ComfyUI) (the codec) and [Qwen3-ASR-ComfyUI](https://huggingface.co/PedroMarinhoDev/Qwen3-ASR-ComfyUI). 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:** pick a voice in **Load Audio** (a few seconds of clean speech, cut between sentences: choose a clip of your own). **Qwen3-ASR Transcribe** writes what it says into **OGG Encode Voice**; to type the transcript yourself, delete that link. Write your text in **OGG TTS Generate**, one line per take; tags such as [sighing] or [excited] go where the delivery should change.\n\n**Keep a voice:** un-mute **Save OGG Voice** (select it, Ctrl+M) and queue once: the voice goes to output/ogg_voices. Next time use **Load OGG Voice** in place of Load Audio, Qwen3-ASR and Encode Voice.\n\n**Settings:** cfg 1-1.5 keeps the voice's natural tempo, 2 speaks faster and more pointedly. Do not clone the voice of a real person without their consent." ] }, { "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": [ 6 ] } ], "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": [ 1, 3 ] } ], "properties": { "Node name for S&R": "OggCodecLoader" }, "widgets_values": [ "drama3_codec.safetensors" ] }, { "id": 4, "type": "LoadAudio", "pos": [ 620, 380 ], "size": [ 360, 136 ], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "localized_name": "audio", "name": "audio", "type": "COMBO", "widget": { "name": "audio" }, "link": null }, { "localized_name": "audioUI", "name": "audioUI", "type": "AUDIO_UI", "widget": { "name": "audioUI" }, "link": null }, { "localized_name": "upload", "name": "upload", "type": "AUDIOUPLOAD", "widget": { "name": "upload" }, "link": null } ], "outputs": [ { "localized_name": "AUDIO", "name": "AUDIO", "type": "AUDIO", "links": [ 2, 9 ] } ], "properties": { "Node name for S&R": "LoadAudio" }, "widgets_values": [ "", "" ] }, { "id": 5, "type": "OggEncodeVoice", "pos": [ 1020, 610 ], "size": [ 400, 108 ], "flags": {}, "order": 4, "mode": 0, "inputs": [ { "localized_name": "codec", "name": "codec", "type": "OGG_CODEC", "link": 1 }, { "localized_name": "audio", "name": "audio", "type": "AUDIO", "link": 2 }, { "localized_name": "transcript", "name": "transcript", "type": "STRING", "widget": { "name": "transcript" }, "link": 10 } ], "outputs": [ { "localized_name": "OGG_VOICE", "name": "OGG_VOICE", "type": "OGG_VOICE", "links": [ 7, 11 ] } ], "properties": { "Node name for S&R": "OggEncodeVoice" }, "widgets_values": [ "Hello! This is a short clip of my voice." ] }, { "id": 6, "type": "OggGenerate", "pos": [ 1020, 20 ], "size": [ 400, 330 ], "flags": {}, "order": 5, "mode": 0, "inputs": [ { "localized_name": "model", "name": "model", "type": "OGG_MODEL", "link": 6 }, { "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": 7 } ], "outputs": [ { "localized_name": "OGG_CODES", "name": "OGG_CODES", "type": "OGG_CODES", "links": [ 4 ] } ], "properties": { "Node name for S&R": "OggGenerate" }, "widgets_values": [ "[frustrated] I told you this would happen.\n[sighing] We should have left an hour ago.\n[playful] But fine, a little adventure never hurt anyone.", "en", 1, "randomize", 6, 1.5, 0.8, true, 0, "", "", 0, 0, 4 ] }, { "id": 7, "type": "OggDecode", "pos": [ 1460, 20 ], "size": [ 260, 78 ], "flags": {}, "order": 6, "mode": 0, "inputs": [ { "localized_name": "codec", "name": "codec", "type": "OGG_CODEC", "link": 3 }, { "localized_name": "codes", "name": "codes", "type": "OGG_CODES", "link": 4 }, { "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": [ 5 ] } ], "properties": { "Node name for S&R": "OggDecode" }, "widgets_values": [ false ] }, { "id": 8, "type": "SaveAudio", "pos": [ 1460, 140 ], "size": [ 360, 112 ], "flags": {}, "order": 7, "mode": 0, "inputs": [ { "localized_name": "audio", "name": "audio", "type": "AUDIO", "link": 5 }, { "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_clone" ] }, { "id": 9, "type": "OggQwen3ASRLoader", "pos": [ 620, 560 ], "size": [ 360, 58 ], "flags": {}, "order": 8, "mode": 0, "inputs": [ { "localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": { "name": "model_name" }, "link": null } ], "outputs": [ { "localized_name": "OGG_ASR_MODEL", "name": "OGG_ASR_MODEL", "type": "OGG_ASR_MODEL", "links": [ 8 ] } ], "properties": { "Node name for S&R": "OggQwen3ASRLoader" }, "widgets_values": [ "qwen3_asr_1.7b_bf16.safetensors" ] }, { "id": 10, "type": "OggQwen3ASRTranscribe", "pos": [ 1020, 380 ], "size": [ 400, 180 ], "flags": {}, "order": 9, "mode": 0, "inputs": [ { "localized_name": "model", "name": "model", "type": "OGG_ASR_MODEL", "link": 8 }, { "localized_name": "audio", "name": "audio", "type": "AUDIO", "link": 9 }, { "localized_name": "language", "name": "language", "type": "COMBO", "widget": { "name": "language" }, "link": null }, { "localized_name": "context", "name": "context", "type": "STRING", "widget": { "name": "context" }, "link": null }, { "localized_name": "max_new_tokens", "name": "max_new_tokens", "type": "INT", "widget": { "name": "max_new_tokens" }, "link": null } ], "outputs": [ { "localized_name": "text", "name": "text", "type": "STRING", "links": [ 10 ] }, { "localized_name": "language", "name": "language", "type": "STRING", "links": null } ], "properties": { "Node name for S&R": "OggQwen3ASRTranscribe" }, "widgets_values": [ "auto", "", 4096 ] }, { "id": 11, "type": "OggSaveVoice", "pos": [ 1460, 610 ], "size": [ 360, 58 ], "flags": {}, "order": 10, "mode": 2, "inputs": [ { "localized_name": "voice", "name": "voice", "type": "OGG_VOICE", "link": 11 }, { "localized_name": "name", "name": "name", "type": "STRING", "widget": { "name": "name" }, "link": null } ], "outputs": [], "properties": { "Node name for S&R": "OggSaveVoice" }, "widgets_values": [ "ogg/voice" ] } ], "links": [ [ 1, 3, 0, 5, 0, "OGG_CODEC" ], [ 2, 4, 0, 5, 1, "AUDIO" ], [ 3, 3, 0, 7, 0, "OGG_CODEC" ], [ 4, 6, 0, 7, 1, "OGG_CODES" ], [ 5, 7, 0, 8, 0, "AUDIO" ], [ 6, 2, 0, 6, 0, "OGG_MODEL" ], [ 7, 5, 0, 6, 14, "OGG_VOICE" ], [ 8, 9, 0, 10, 0, "OGG_ASR_MODEL" ], [ 9, 4, 0, 10, 1, "AUDIO" ], [ 10, 10, 0, 5, 2, "STRING" ], [ 11, 5, 0, 11, 0, "OGG_VOICE" ] ], "groups": [], "config": {}, "extra": { "ds": { "scale": 0.75, "offset": [ 0, 0 ] } }, "version": 0.4 }