| { |
| "id": "f679c5fd-3166-4e0d-a677-365554b45311", |
| "revision": 0, |
| "last_node_id": 8, |
| "last_link_id": 6, |
| "nodes": [ |
| { |
| "id": 1, |
| "type": "MarkdownNote", |
| "pos": [ |
| 20, |
| 20 |
| ], |
| "size": [ |
| 560, |
| 520 |
| ], |
| "flags": {}, |
| "order": 0, |
| "mode": 0, |
| "inputs": [], |
| "outputs": [], |
| "properties": {}, |
| "widgets_values": [ |
| "## OGG TTS · find a voice\n\nOGG cannot be told a voice in words. What it has: **3157 trained speakers** (`spk_0` ... `spk_3156`, anonymous), **599 recordings** (`q0` ... `q598`, each a book or a game, with its room and manner) and an unknown-speaker token per language (`ru_x`).\n\n**Audition:** `speaker` in OGG TTS Generate is `random`: every run takes another seed, so another speaker (the console says which: `speaker token spk_N`). Every run saves the take (output/ogg/design) and, beside it, its voice (output/ogg_voices/ogg/design): matching numbers. Listen, keep the ones you like, delete the others.\n\n**Keep a voice:** the saved voice is a clip of that take with its transcript. Load it with **Load OGG Voice** in OGG TTS Generate or OGG TTS Dialogue: the speaker then stays the same for any text. To explore recordings instead of speakers, fill `quality` (e.g. q35) and keep `speaker` as it is.\n\nFiles: see the other OGG workflows. This one needs no Qwen3-ASR: the transcript is the text you wrote." |
| ] |
| }, |
| { |
| "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, |
| 5 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggGenerate" |
| }, |
| "widgets_values": [ |
| "[excited] Hello! This is a short line to hear how I sound.", |
| "en", |
| 1, |
| "randomize", |
| 6, |
| 1.5, |
| 0.8, |
| true, |
| 0, |
| "random", |
| "", |
| 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/design/take" |
| ] |
| }, |
| { |
| "id": 7, |
| "type": "OggVoiceFromTake", |
| "pos": [ |
| 1020, |
| 400 |
| ], |
| "size": [ |
| 400, |
| 100 |
| ], |
| "flags": {}, |
| "order": 6, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "codes", |
| "name": "codes", |
| "type": "OGG_CODES", |
| "link": 5 |
| }, |
| { |
| "localized_name": "take", |
| "name": "take", |
| "type": "INT", |
| "widget": { |
| "name": "take" |
| }, |
| "link": null |
| }, |
| { |
| "localized_name": "strip_tags", |
| "name": "strip_tags", |
| "type": "BOOLEAN", |
| "widget": { |
| "name": "strip_tags" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [ |
| { |
| "localized_name": "OGG_VOICE", |
| "name": "OGG_VOICE", |
| "type": "OGG_VOICE", |
| "links": [ |
| 6 |
| ] |
| } |
| ], |
| "properties": { |
| "Node name for S&R": "OggVoiceFromTake" |
| }, |
| "widgets_values": [ |
| 0, |
| true |
| ] |
| }, |
| { |
| "id": 8, |
| "type": "OggSaveVoice", |
| "pos": [ |
| 1460, |
| 400 |
| ], |
| "size": [ |
| 360, |
| 80 |
| ], |
| "flags": {}, |
| "order": 7, |
| "mode": 0, |
| "inputs": [ |
| { |
| "localized_name": "voice", |
| "name": "voice", |
| "type": "OGG_VOICE", |
| "link": 6 |
| }, |
| { |
| "localized_name": "name", |
| "name": "name", |
| "type": "STRING", |
| "widget": { |
| "name": "name" |
| }, |
| "link": null |
| } |
| ], |
| "outputs": [], |
| "properties": { |
| "Node name for S&R": "OggSaveVoice" |
| }, |
| "widgets_values": [ |
| "ogg/design/voice" |
| ] |
| } |
| ], |
| "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" |
| ], |
| [ |
| 5, |
| 4, |
| 0, |
| 7, |
| 0, |
| "OGG_CODES" |
| ], |
| [ |
| 6, |
| 7, |
| 0, |
| 8, |
| 0, |
| "OGG_VOICE" |
| ] |
| ], |
| "groups": [], |
| "config": {}, |
| "extra": { |
| "ds": { |
| "scale": 0.75, |
| "offset": [ |
| 0, |
| 0 |
| ] |
| } |
| }, |
| "version": 0.4 |
| } |
