| { |
| "id": "7c13b113-86af-4f87-bc36-856a6e0d5d62", |
| "revision": 0, |
| "last_node_id": 13, |
| "last_link_id": 16, |
| "nodes": [ |
| { |
| "id": 1, |
| "type": "MarkdownNote", |
| "pos": [ |
| 20, |
| 20 |
| ], |
| "size": [ |
| 560, |
| 620 |
| ], |
| "flags": {}, |
| "order": 0, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "properties": {}, |
| "widgets_values": [ |
| "## OGG TTS · dialogue, a voice for every speaker\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)<br>or qwen3_asr_0.6b_bf16.safetensors (1.6 GB) | models/asr |\n\n**How to use:** pick one clip per speaker in the two **Load Audio** nodes (a few seconds of clean speech each; your own clips). Each **Qwen3-ASR Transcribe** writes what its clip says into **OGG Encode Voice**. In **OGG TTS Dialogue** the speakers are named in `name_1`, `name_2`... (without case) and their voices connect to `voice_1`, `voice_2`...; the script is one turn per line, `Name: [tag] text`. A line with no name goes on with the speaker before it. Tags as in OGG TTS Generate.\n\n**Modes:** *line by line* generates every line from its speaker's voice and lets it hear the two lines before and after it; it is the safe one. *one pass* gives the model the whole scene and all the voices at once (its dialogue mode): one take, no line timing in the editor, and less tried; it is experimental: the authors document only line by line. Up to 6 speakers; a speaker used in the script needs a voice.\n\nDo 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": [ |
| 11 |
| ] |
| } |
| ], |
| "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, |
| 2, |
| 14 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggCodecLoader" |
| }, |
| "widgets_values": [ |
| "drama3_codec.safetensors" |
| ] |
| }, |
| { |
| "id": 4, |
| "type": "OggQwen3ASRLoader", |
| "pos": [ |
| 620, |
| 280 |
| ], |
| "size": [ |
| 360, |
| 58 |
| ], |
| "flags": {}, |
| "order": 3, |
| "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": [ |
| 5, |
| 6 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggQwen3ASRLoader" |
| }, |
| "widgets_values": [ |
| "qwen3_asr_1.7b_bf16.safetensors" |
| ] |
| }, |
| { |
| "id": 5, |
| "type": "LoadAudio", |
| "pos": [ |
| 620, |
| 400 |
| ], |
| "size": [ |
| 360, |
| 136 |
| ], |
| "flags": {}, |
| "order": 4, |
| "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": [ |
| 3, |
| 7 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "LoadAudio" |
| }, |
| "widgets_values": [ |
| "", |
| "" |
| ] |
| }, |
| { |
| "id": 6, |
| "type": "LoadAudio", |
| "pos": [ |
| 620, |
| 600 |
| ], |
| "size": [ |
| 360, |
| 136 |
| ], |
| "flags": {}, |
| "order": 5, |
| "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": [ |
| 4, |
| 8 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "LoadAudio" |
| }, |
| "widgets_values": [ |
| "", |
| "" |
| ] |
| }, |
| { |
| "id": 7, |
| "type": "OggQwen3ASRTranscribe", |
| "pos": [ |
| 1020, |
| 400 |
| ], |
| "size": [ |
| 400, |
| 180 |
| ], |
| "flags": {}, |
| "order": 6, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "model", |
| "name": "model", |
| "type": "OGG_ASR_MODEL", |
| "link": 5 |
| }, |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 7 |
| }, |
| { |
| "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": [ |
| 9 |
| ] |
| }, |
| { |
| "localized_name": "language", |
| "name": "language", |
| "type": "STRING", |
| "links": null |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggQwen3ASRTranscribe" |
| }, |
| "widgets_values": [ |
| "auto", |
| "", |
| 4096 |
| ] |
| }, |
| { |
| "id": 8, |
| "type": "OggQwen3ASRTranscribe", |
| "pos": [ |
| 1020, |
| 620 |
| ], |
| "size": [ |
| 400, |
| 180 |
| ], |
| "flags": {}, |
| "order": 7, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "model", |
| "name": "model", |
| "type": "OGG_ASR_MODEL", |
| "link": 6 |
| }, |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 8 |
| }, |
| { |
| "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": 9, |
| "type": "OggEncodeVoice", |
| "pos": [ |
| 1460, |
| 400 |
| ], |
| "size": [ |
| 400, |
| 108 |
| ], |
| "flags": {}, |
| "order": 8, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codec", |
| "name": "codec", |
| "type": "OGG_CODEC", |
| "link": 1 |
| }, |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 3 |
| }, |
| { |
| "localized_name": "transcript", |
| "name": "transcript", |
| "type": "STRING", |
| "widget": { |
| "name": "transcript" |
| }, |
| "link": 9 |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_VOICE", |
| "name": "OGG_VOICE", |
| "type": "OGG_VOICE", |
| "links": [ |
| 12 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggEncodeVoice" |
| }, |
| "widgets_values": [ |
| "Hello! This is the first speaker." |
| ] |
| }, |
| { |
| "id": 10, |
| "type": "OggEncodeVoice", |
| "pos": [ |
| 1460, |
| 620 |
| ], |
| "size": [ |
| 400, |
| 108 |
| ], |
| "flags": {}, |
| "order": 9, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codec", |
| "name": "codec", |
| "type": "OGG_CODEC", |
| "link": 2 |
| }, |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 4 |
| }, |
| { |
| "localized_name": "transcript", |
| "name": "transcript", |
| "type": "STRING", |
| "widget": { |
| "name": "transcript" |
| }, |
| "link": 10 |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_VOICE", |
| "name": "OGG_VOICE", |
| "type": "OGG_VOICE", |
| "links": [ |
| 13 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggEncodeVoice" |
| }, |
| "widgets_values": [ |
| "Hello! This is the second speaker." |
| ] |
| }, |
| { |
| "id": 11, |
| "type": "OggDialogue", |
| "pos": [ |
| 1020, |
| 20 |
| ], |
| "size": [ |
| 400, |
| 330 |
| ], |
| "flags": {}, |
| "order": 10, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "model", |
| "name": "model", |
| "type": "OGG_MODEL", |
| "link": 11 |
| }, |
| { |
| "localized_name": "script", |
| "name": "script", |
| "type": "STRING", |
| "widget": { |
| "name": "script" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "language", |
| "name": "language", |
| "type": "COMBO", |
| "widget": { |
| "name": "language" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "mode", |
| "name": "mode", |
| "type": "COMBO", |
| "widget": { |
| "name": "mode" |
| }, |
| "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": "max_frames", |
| "name": "max_frames", |
| "type": "INT", |
| "widget": { |
| "name": "max_frames" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_1", |
| "name": "name_1", |
| "type": "STRING", |
| "widget": { |
| "name": "name_1" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_2", |
| "name": "name_2", |
| "type": "STRING", |
| "widget": { |
| "name": "name_2" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_3", |
| "name": "name_3", |
| "type": "STRING", |
| "widget": { |
| "name": "name_3" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_4", |
| "name": "name_4", |
| "type": "STRING", |
| "widget": { |
| "name": "name_4" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_5", |
| "name": "name_5", |
| "type": "STRING", |
| "widget": { |
| "name": "name_5" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "name_6", |
| "name": "name_6", |
| "type": "STRING", |
| "widget": { |
| "name": "name_6" |
| }, |
| "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": "dialogue_layout", |
| "name": "dialogue_layout", |
| "type": "COMBO", |
| "widget": { |
| "name": "dialogue_layout" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_1", |
| "name": "speaker_1", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_1" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_2", |
| "name": "speaker_2", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_2" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_3", |
| "name": "speaker_3", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_3" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_4", |
| "name": "speaker_4", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_4" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_5", |
| "name": "speaker_5", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_5" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "speaker_6", |
| "name": "speaker_6", |
| "type": "STRING", |
| "widget": { |
| "name": "speaker_6" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "voice_1", |
| "name": "voice_1", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": 12 |
| }, |
| { |
| "localized_name": "voice_2", |
| "name": "voice_2", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": 13 |
| }, |
| { |
| "localized_name": "voice_3", |
| "name": "voice_3", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": null |
| }, |
| { |
| "localized_name": "voice_4", |
| "name": "voice_4", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": null |
| }, |
| { |
| "localized_name": "voice_5", |
| "name": "voice_5", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": null |
| }, |
| { |
| "localized_name": "voice_6", |
| "name": "voice_6", |
| "type": "OGG_VOICE", |
| "shape": 7, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_CODES", |
| "name": "OGG_CODES", |
| "type": "OGG_CODES", |
| "links": [ |
| 15 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggDialogue" |
| }, |
| "widgets_values": [ |
| "Жан: [excited] Привет, меня зовут Жан и я — авантюрист.\nМария: [sighing] Ты так говоришь каждому встречному.\nЖан: [laughing] Только тем, кто спрашивает.", |
| "ru", |
| "line by line", |
| 1, |
| "randomize", |
| 6, |
| 1.5, |
| 0.8, |
| 0, |
| "Жан", |
| "Мария", |
| "", |
| "", |
| "", |
| "", |
| "", |
| 0, |
| 0, |
| 4, |
| "as trained", |
| "", |
| "", |
| "", |
| "", |
| "", |
| "" |
| ] |
| }, |
| { |
| "id": 12, |
| "type": "OggDecode", |
| "pos": [ |
| 1900, |
| 20 |
| ], |
| "size": [ |
| 260, |
| 78 |
| ], |
| "flags": {}, |
| "order": 11, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codec", |
| "name": "codec", |
| "type": "OGG_CODEC", |
| "link": 14 |
| }, |
| { |
| "localized_name": "codes", |
| "name": "codes", |
| "type": "OGG_CODES", |
| "link": 15 |
| }, |
| { |
| "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": [ |
| 16 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggDecode" |
| }, |
| "widgets_values": [ |
| false |
| ] |
| }, |
| { |
| "id": 13, |
| "type": "SaveAudio", |
| "pos": [ |
| 1900, |
| 140 |
| ], |
| "size": [ |
| 360, |
| 112 |
| ], |
| "flags": {}, |
| "order": 12, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "audio", |
| "name": "audio", |
| "type": "AUDIO", |
| "link": 16 |
| }, |
| { |
| "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_dialogue" |
| ] |
| } |
| ], |
| "links": [ |
| [ |
| 1, |
| 3, |
| 0, |
| 9, |
| 0, |
| "OGG_CODEC" |
| ], |
| [ |
| 2, |
| 3, |
| 0, |
| 10, |
| 0, |
| "OGG_CODEC" |
| ], |
| [ |
| 3, |
| 5, |
| 0, |
| 9, |
| 1, |
| "AUDIO" |
| ], |
| [ |
| 4, |
| 6, |
| 0, |
| 10, |
| 1, |
| "AUDIO" |
| ], |
| [ |
| 5, |
| 4, |
| 0, |
| 7, |
| 0, |
| "OGG_ASR_MODEL" |
| ], |
| [ |
| 6, |
| 4, |
| 0, |
| 8, |
| 0, |
| "OGG_ASR_MODEL" |
| ], |
| [ |
| 7, |
| 5, |
| 0, |
| 7, |
| 1, |
| "AUDIO" |
| ], |
| [ |
| 8, |
| 6, |
| 0, |
| 8, |
| 1, |
| "AUDIO" |
| ], |
| [ |
| 9, |
| 7, |
| 0, |
| 9, |
| 2, |
| "STRING" |
| ], |
| [ |
| 10, |
| 8, |
| 0, |
| 10, |
| 2, |
| "STRING" |
| ], |
| [ |
| 11, |
| 2, |
| 0, |
| 11, |
| 0, |
| "OGG_MODEL" |
| ], |
| [ |
| 12, |
| 9, |
| 0, |
| 11, |
| 26, |
| "OGG_VOICE" |
| ], |
| [ |
| 13, |
| 10, |
| 0, |
| 11, |
| 27, |
| "OGG_VOICE" |
| ], |
| [ |
| 14, |
| 3, |
| 0, |
| 12, |
| 0, |
| "OGG_CODEC" |
| ], |
| [ |
| 15, |
| 11, |
| 0, |
| 12, |
| 1, |
| "OGG_CODES" |
| ], |
| [ |
| 16, |
| 12, |
| 0, |
| 13, |
| 0, |
| "AUDIO" |
| ] |
| ], |
| "groups": [], |
| "config": {}, |
| "extra": { |
| "ds": { |
| "scale": 0.75, |
| "offset": [ |
| 0, |
| 0 |
| ] |
| } |
| }, |
| "version": 0.4 |
| } |
