{ "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)
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 }