{"schema":"record/v1","id":"src_01M569MKN0EXEMDFMX4J0DZG5T","type":"source","revision":1,"etag":"\"r1.s0\"","title":"Style-Bert-VITS2 (litagin02): Bert-VITS2 with controllable voice styles, Japanese TTS and training UI","summary":null,"status":"active","body":{"text":"Pretrained base model record: hf--litagin--style-bert-vits2-2-0-base-jp-extra. Default voice models bundled at install time carry their own terms (JVNV corpus CC BY-SA 4.0; あみたろ/小春音アミ with credit requirement) per docs/TERMS_OF_USE.md.","archived":false,"revision":{"ref":"2.7.0 (latest release, published 2025-08-24)","pinned":true,"source_url":"https://github.com/litagin02/Style-Bert-VITS2/releases"},"checked_at":"2026-10-17T00:00:00.000Z","parent_url":"https://github.com/fishaudio/Bert-VITS2","usefulness":"Japanese-first expressive TTS built on Bert-VITS2 v2.1 and JP-Extra, with style vectors, model merging, ONNX export, a training WebUI and an API server. Runs synthesis and merging on CPU and trains on NVIDIA GPUs; code is AGPL-3.0, and the README plus a terms file add model-level obligations (CC BY-SA 4.0 for the default JVNV-based voices, credit lines for the Amitaro model).","source_type":"repository","availability":"available","dependencies":["Python","PyTorch","Bert-VITS2 lineage","pip package style-bert-vits2 for inference only"],"source_owner":"litagin02 (individual developer; Japanese-language README)","canonical_url":"https://github.com/litagin02/style-bert-vits2","next_check_at":"2026-10-31T00:00:00.000Z","successor_url":null,"hardware_notes":"README: synthesis works on CPU without a GPU; training needs an NVIDIA GPU; merging and synthesis work without one; CPU install script provided. No VRAM numbers read.","known_limitations":["AGPL-3.0 network-copyleft applies to code; the repository also carries LGPL-3.0 text for text/user_dict derived from VOICEVOX engine.","The terms file separates non-binding requests (\"お願い\") from binding model terms; only the model terms and the repository license bind.","The pretrained base weights are derived from Bert-VITS2 (Fish Audio) models and are labelled AGPL-3.0 on Hugging Face; provenance and licenses of the training data of those base models were not traced.","The owner's location was not verified; the project is Japan-focused and documented in Japanese."],"upstream_updated_at":"2025-12-07T13:06:59.000Z"},"categories":["T13","T09"],"tags":["level:advanced","lang:ja","kind:tts-model-code","task:text-to-speech","task:voice-training","task:japanese-speech","ecosystem:bert-vits2","hardware:cpu-inference"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"The README says the project modifies Bert-VITS2 v2.1 and Japanese-Extra to let users control emotion and speaking style, and that synthesis alone works on CPU without a graphics card.","locator":"README, 概要","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"Without an NVIDIA GPU, training is not possible but synthesis and model merging still work.","locator":"README, 動作環境","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"The repository is licensed under AGPL-3.0, the same as Bert-VITS2, with text/user_dict under LGPL v3.","locator":"README, LICENSE","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"The default JVNV-corpus-based models (jvnv-F1-jp, F2, M1, M2) inherit the corpus license CC BY-SA 4.0.","locator":"docs/TERMS_OF_USE.md, モデルの利用規約・ライセンス, JVNVコーパス","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"For the 小春音アミ/あみたろ models, published generated audio must carry a credit that the voice is based on あみたろの声素材工房, with use cases such as age-restricted works and treating output as the speaker's own voice prohibited.","locator":"docs/TERMS_OF_USE.md, 小春音アミ / あみたろ","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"The terms file says the sections before the model terms are non-binding requests (not prohibitions) and that only the repository license binds for repository use; requests include no deepfake/impersonation use.","locator":"docs/TERMS_OF_USE.md, header","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub API returns the repository record for litagin02/Style-Bert-VITS2: default branch master; pushed_at at check time 2025-12-07T13:06:59Z (raw response saved under evidence/github/litagin02--style-bert-vits2.json).","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, default_branch (pushed_at is volatile)","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub API reports archived = false for litagin02/Style-Bert-VITS2.","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, archived","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub license detection for litagin02/Style-Bert-VITS2 returns spdx_id AGPL-3.0.","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, license","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2/releases/latest","claim":"GitHub API latest release for litagin02/Style-Bert-VITS2: tag 2.7.0 published 2025-08-24T03:01:47Z (selected fields of the response saved under evidence/github/litagin02--style-bert-vits2.release.json).","locator":"GitHub API repos/litagin02/Style-Bert-VITS2/releases/latest, tag_name","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"AGPL-3.0 with LGPL-3.0 for text/user_dict. Network-use source-offer duty; GitHub detects AGPL-3.0. Does not address training.","hosting":"permitted","component":"code","license_id":"AGPL-3.0-only","modification":"restricted","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2#readme"],"model_training":"unknown","redistribution":"restricted"},{"notes":"Not the repository license: base weights are labelled AGPL-3.0 on Hugging Face; default JVNV-based voices inherit CC BY-SA 4.0 (ShareAlike); the Amitaro voice models require a credit and forbid listed uses and have merge limits (25 percent or more Amitaro share keeps their terms). Check each model's terms.","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-per-model-terms","modification":"restricted","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","https://huggingface.co/api/models/litagin/Style-Bert-VITS2-2.0-base-JP-Extra"],"model_training":"unknown","redistribution":"restricted"},{"notes":"outputs: credit lines are required when publishing audio from the Amitaro-based models (example \"Style-BertVITS2モデル: 小春音アミ、あみたろの声素材工房 (https://amitaro.net/)\"); the JVNV models carry CC BY-SA 4.0 obligations; project requests ask not to use for impersonation or deepfakes.","hosting":"not_applicable","component":"other","license_id":"LicenseRef-per-model-terms","modification":"not_applicable","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md"],"model_training":"unknown","redistribution":"not_applicable"}],"attribution":{"origin":"research_agent","upstream_owner":"litagin02 (individual developer; Japanese-language README)","upstream_url":"https://github.com/litagin02/style-bert-vits2","imported_from":"content/seeds/research/wave-2/resources.jsonl#litagin02--style-bert-vits2","import_batch_id":"l07-wave-2-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-wave-2-2026-10-17","original":{"id":"litagin02--style-bert-vits2","name":"Style-Bert-VITS2 (litagin02): Bert-VITS2 with controllable voice styles, Japanese TTS and training UI","tags":["level:advanced","lang:ja","kind:tts-model-code","task:text-to-speech","task:voice-training","task:japanese-speech","ecosystem:bert-vits2","hardware:cpu-inference"],"notes":"Pretrained base model record: hf--litagin--style-bert-vits2-2-0-base-jp-extra. Default voice models bundled at install time carry their own terms (JVNV corpus CC BY-SA 4.0; あみたろ/小春音アミ with credit requirement) per docs/TERMS_OF_USE.md.","rights":[{"notes":"AGPL-3.0 with LGPL-3.0 for text/user_dict. Network-use source-offer duty; GitHub detects AGPL-3.0. Does not address training.","hosting":"permitted","component":"code","license_id":"AGPL-3.0-only","modification":"restricted","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2#readme"],"model_training":"unknown","redistribution":"restricted"},{"notes":"Not the repository license: base weights are labelled AGPL-3.0 on Hugging Face; default JVNV-based voices inherit CC BY-SA 4.0 (ShareAlike); the Amitaro voice models require a credit and forbid listed uses and have merge limits (25 percent or more Amitaro share keeps their terms). Check each model's terms.","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-per-model-terms","modification":"restricted","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","https://huggingface.co/api/models/litagin/Style-Bert-VITS2-2.0-base-JP-Extra"],"model_training":"unknown","redistribution":"restricted"},{"notes":"outputs: credit lines are required when publishing audio from the Amitaro-based models (example \"Style-BertVITS2モデル: 小春音アミ、あみたろの声素材工房 (https://amitaro.net/)\"); the JVNV models carry CC BY-SA 4.0 obligations; project requests ask not to use for impersonation or deepfakes.","hosting":"not_applicable","component":"other","license_id":"LicenseRef-per-model-terms","modification":"not_applicable","evidence_urls":["https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md"],"model_training":"unknown","redistribution":"not_applicable"}],"archived":false,"evidence":[{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"The README says the project modifies Bert-VITS2 v2.1 and Japanese-Extra to let users control emotion and speaking style, and that synthesis alone works on CPU without a graphics card.","locator":"README, 概要","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"Without an NVIDIA GPU, training is not possible but synthesis and model merging still work.","locator":"README, 動作環境","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2#readme","claim":"The repository is licensed under AGPL-3.0, the same as Bert-VITS2, with text/user_dict under LGPL v3.","locator":"README, LICENSE","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"The default JVNV-corpus-based models (jvnv-F1-jp, F2, M1, M2) inherit the corpus license CC BY-SA 4.0.","locator":"docs/TERMS_OF_USE.md, モデルの利用規約・ライセンス, JVNVコーパス","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"For the 小春音アミ/あみたろ models, published generated audio must carry a credit that the voice is based on あみたろの声素材工房, with use cases such as age-restricted works and treating output as the speaker's own voice prohibited.","locator":"docs/TERMS_OF_USE.md, 小春音アミ / あみたろ","classification":"sourced_fact"},{"url":"https://github.com/litagin02/Style-Bert-VITS2/blob/master/docs/TERMS_OF_USE.md","claim":"The terms file says the sections before the model terms are non-binding requests (not prohibitions) and that only the repository license binds for repository use; requests include no deepfake/impersonation use.","locator":"docs/TERMS_OF_USE.md, header","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub API returns the repository record for litagin02/Style-Bert-VITS2: default branch master; pushed_at at check time 2025-12-07T13:06:59Z (raw response saved under evidence/github/litagin02--style-bert-vits2.json).","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, default_branch (pushed_at is volatile)","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub API reports archived = false for litagin02/Style-Bert-VITS2.","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, archived","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2","claim":"GitHub license detection for litagin02/Style-Bert-VITS2 returns spdx_id AGPL-3.0.","locator":"GitHub API repos/litagin02/Style-Bert-VITS2, license","classification":"sourced_fact"},{"url":"https://api.github.com/repos/litagin02/Style-Bert-VITS2/releases/latest","claim":"GitHub API latest release for litagin02/Style-Bert-VITS2: tag 2.7.0 published 2025-08-24T03:01:47Z (selected fields of the response saved under evidence/github/litagin02--style-bert-vits2.release.json).","locator":"GitHub API repos/litagin02/Style-Bert-VITS2/releases/latest, tag_name","classification":"sourced_fact"}],"language":"ja","revision":{"ref":"2.7.0 (latest release, published 2025-08-24)","pinned":true,"source_url":"https://github.com/litagin02/Style-Bert-VITS2/releases"},"checked_on":"2026-10-17","parent_url":"https://github.com/fishaudio/Bert-VITS2","usefulness":"Japanese-first expressive TTS built on Bert-VITS2 v2.1 and JP-Extra, with style vectors, model merging, ONNX export, a training WebUI and an API server. Runs synthesis and merging on CPU and trains on NVIDIA GPUs; code is AGPL-3.0, and the README plus a terms file add model-level obligations (CC BY-SA 4.0 for the default JVNV-based voices, credit lines for the Amitaro model).","source_type":"repository","category_ids":["T13","T09"],"dependencies":["Python","PyTorch","Bert-VITS2 lineage","pip package style-bert-vits2 for inference only"],"source_owner":"litagin02 (individual developer; Japanese-language README)","canonical_url":"https://github.com/litagin02/Style-Bert-VITS2","review_status":"reviewed","successor_url":null,"hardware_notes":"README: synthesis works on CPU without a GPU; training needs an NVIDIA GPU; merging and synthesis work without one; CPU install script provided. No VRAM numbers read.","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["AGPL-3.0 network-copyleft applies to code; the repository also carries LGPL-3.0 text for text/user_dict derived from VOICEVOX engine.","The terms file separates non-binding requests (\"お願い\") from binding model terms; only the model terms and the repository license bind.","The pretrained base weights are derived from Bert-VITS2 (Fish Audio) models and are labelled AGPL-3.0 on Hugging Face; provenance and licenses of the training data of those base models were not traced.","The owner's location was not verified; the project is Japan-focused and documented in Japanese."],"upstream_updated_at":"2025-12-07T13:06:59Z","proposed_next_action":"synthesize"},"collector":{"id":"litagin02--style-bert-vits2","file":"research-results/L07/wave-2/w2-ja/resources.jsonl","kind":"resource","lane":"w2-ja","wave":"l07-wave-2-2026-10-17","collector":"Claude Sonnet 5.5, wave-2 lane w2-ja (Japanese media ecosystem), dispatched by the L07 session, founder-run","merged_from":[],"original_id":"litagin02--style-bert-vits2","review_reason":"L07 wave 2: lane w2-ja accepted after validation (0 errors; 5 deliberate trailing-slash warnings), automated metadata re-check and quote verification: 201/208 quotes found mechanically on live pages; the 5 JFTC PDF quotes were matched mechanically in the fetch tool's saved copy (host returns 403 to curl); the JFTC terms quote was confirmed by the fetch tool only; one JVS quote differs by a hyphen (page reads 'CC BY-SA 4.0'). Rights normalized by L07 after reading PDL 1.0.","review_status":"reviewed"},"observed_on":"2026-10-17","original_id":"litagin02--style-bert-vits2","source_file":"content/seeds/research/wave-2/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"ja","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"synthesize"},"source_schema":"resource-candidate/0.1","original_sha256":"5f6b3209deb52b511ba29b7a92ceb9fc44c006c704ad78251957987b80428888","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569MKN0EXEMDFMX4J0DZG5T","api_url":"https://veyrul.com/v1/records/src_01M569MKN0EXEMDFMX4J0DZG5T","created_at":"2026-10-18T01:22:23.509Z","updated_at":"2026-10-18T01:22:23.509Z","last_activity_at":"2026-10-18T01:22:23.509Z"}