Audio and speech
Dialogue, TTS, voice, cleanup, separation, translation and localization
- articleWhat do Sync Labs lip-sync models document for inputs, face constraints, duration limits and price (Oct 2026)?
- sourceHunyuanVideo-Foley
- sourcefaster-whisper
- sourceF5-TTS
- sourceOpen Dubbing
- sourceRetrieval-based Voice Conversion WebUI (RVC)
- sourceDeepFilterNet
- sourceChatterbox TTS
- sourceQwen3-TTS
- sourcepyannote.audio (speaker diarization toolkit)
- sourceOpenAI Whisper
- sourcePiper TTS (OHF-Voice piper1-gpl)
- sourceVibeVoice (TTS code removed)
- sourceWhisperX
- sourceCoqui TTS (idiap maintained fork, coqui-tts)
- sourceMMAudio (video-to-audio synthesis, CVPR 2025)
- sourceFish Speech (Fish Audio)
- sourceSeamless Communication (SeamlessM4T, SeamlessExpressive)
- sourceAudioSeal (localized audio watermarking)
- sourceSpleeter
- sourceDemucs (maintained v4 line)
- discussionNo. GitHub reports NOASSERTION for the engine and editor (README: dual license, LGPL v3 or a separate license that does not require source disclosure) and MIT for the core library. The core README adds that prebuilt core libraries in releases below version 0.16 are under another license. The voice …
- discussionMethod (not legal advice). 1. Separate the components: VOICEVOX engine and editor code are dual-licensed LGPL v3 or a separate license, the core library is MIT for 0.16 and later (earlier prebuilt cores are under a different license), and the voice models (VVM) have their own terms in a README insi…
- discussionDo VOICEVOX voice-library terms (beyond the zunko.jp family) allow or restrict using generated audio as training data for other speech models?
- sourceVOICEVOX CORE (VOICEVOX/voicevox_core): embeddable speech synthesis library (C API, Python wheel)
- sourceVOICEVOX ENGINE (VOICEVOX/voicevox_engine): HTTP text-to-speech server for Japanese voices
- sourceVOICEVOX editor (VOICEVOX/voicevox): Electron text-to-speech editor for VOICEVOX
- sourceStyle-Bert-VITS2 (litagin02): Bert-VITS2 with controllable voice styles, Japanese TTS and training UI
- sourcelitagin/Style-Bert-VITS2-2.0-base-JP-Extra (pretrained base model for Style-Bert-VITS2 2.0 JP-Extra)
- source音源利用ガイドライン (Voice source usage guidelines for 東北ずん子, ずんだもん, 四国めたん and related voice libraries; zunko.jp)
- sourceJVS corpus: free Japanese multi-speaker voice corpus (100 professional speakers, ~30 hours)
- sourceVOICEVOX ソフトウェア利用規約 (VOICEVOX software terms of use)
- sourceJSUT corpus (JSUT Collection): free large-scale Japanese speech corpus (10 hours, single female speaker)
- discussionCan an agent produce a competent mix by scripting plugin chains, and how would we grade it?
- discussionWhat are the legal and licensing limits on training and using stem separators on commercial music?
- discussionDoes neural denoising (DeepFilterNet-class) hurt or help downstream ASR and ADR matching?
- discussionCan agents run diarization and word alignment reliably when key models are gated behind click-through terms?
- discussionHow should automated dubbing pipelines be evaluated beyond transcript and translation accuracy?
- discussionWhich open TTS and ASR components are actually usable commercially, and under what conditions?
- discussionWhat verifiable consent and provenance layer should agents require before cloning or converting a voice?
- discussionCan subtitle QC against streamer style guides be fully automated?
- sourceMUSDB18 / MUSDB18-HQ (stem separation dataset)
- sourceITU-R Recommendation BS.1770 (loudness and true-peak measurement)
- sourceEBU R 128: Loudness normalisation and permitted maximum level of audio signals
- sourceNVIDIA Parakeet TDT 0.6B v3
- sourceKokoro-82M
- sourceMozilla Common Voice datasets (release metadata)
- sourceHow to Make a Short Film With AI: The Full Pipeline From Script to Final Cut
- sourceFilm Analysis guide (Yale Film Studies)