Skip to content
Change the repository type filter

All

    Repositories list

    • MOSS-VA-v2 conditioning manual: 40 emotions (best prompt + LoRA merge %, reward, correlations) — MD skill + HTML
      HTML
      0000Updated Aug 9, 2026Aug 9, 2026
    • Conditioned speech corpus generator: 808 conditions per voice, EN+DE paired, with demo grid
      HTML
      0000Updated Aug 9, 2026Aug 9, 2026
    • Emotion x voice x delivery-condition study on MOSS-TTS voice-acting: 6 voices, 40 emotions, 4 conditions, best-of-32.
      HTML
      0000Updated Aug 9, 2026Aug 9, 2026
    • Reference-voice search demo — 1336 Gemini-annotated character voices, semantic + BM25 search
      Python
      0000Updated Aug 7, 2026Aug 7, 2026
    • MOSS-VA-v2 VoiceNet dimension-LoRA conditioning manual (dose-response, side-effects, audio)
      HTML
      0000Updated Aug 6, 2026Aug 6, 2026
    • Reinterpreted German reference voices (Mediathek-derived, synthetic)
      0100Updated Aug 6, 2026Aug 6, 2026
    • MOSS voice-acting: Hollywood casting-session agent runs — multi-part 30s performances, speaker continuity, prompts and scores per take
      0000Updated Aug 6, 2026Aug 6, 2026
    • LAION MOSS Local-Transformer 1.5 voice-acting model (4.55B, 48 kHz) — inference, fast-inference guide, best-of-64 audio demos
      Python
      Apache License 2.0
      0300Updated Aug 6, 2026Aug 6, 2026
    • 1000 reinterpreted reference voices (cluster->SIDON->pitch->MOSS reinterpretation)
      0000Updated Aug 5, 2026Aug 5, 2026
    • Voice reinterpretation training-data preview (original + top-10 expressive re-performances, procedural captions + scores)
      0000Updated Aug 5, 2026Aug 5, 2026
    • Reference-voice reinterpretation before/after preview
      0000Updated Aug 4, 2026Aug 4, 2026
    • ±10% pitch-shift before/after grid for reference-voice de-identification
      0000Updated Aug 4, 2026Aug 4, 2026
    • VoiceCLAP text->audio search over 50k annotated voice samples
      0000Updated Aug 4, 2026Aug 4, 2026
    • Autonomous NSFW-emotion optimization grid (18+, synthetic)
      0000Updated Aug 3, 2026Aug 3, 2026
    • Autonomous LLM-driven search agent for LoRA+prompt strategies on MOSS-VA-v2 voice acting TTS
      Python
      0000Updated Aug 3, 2026Aug 3, 2026
    • NSFW explicitness LoRA dose-sweep grid (audio + stats) for MOSS-VA-v2 — 18+
      0000Updated Aug 3, 2026Aug 3, 2026
    • Procedural voice-acting captions from expert VoiceNet/EmoNet/genuineness/vocal-burst scores: terse tags, inline detected bursts (locator@0.75 -> confirm -> dura…
      Python
      0000Updated Aug 1, 2026Aug 1, 2026
    • VoiceNet dimension LoRAs — high vs low contrast grid
      HTML
      0000Updated Aug 1, 2026Aug 1, 2026
    • Collection of three complementary voice taxonomies: VoiceNet (59 speech dimensions), EmoNet (40 emotion categories), VocalBurst (82 non-speech sounds)
      HTML
      0600Updated Aug 1, 2026Aug 1, 2026
    • 266 voice-acting edge cases: coaching notes, acoustic signatures and detector tokens for expressive-speech generation and annotation
      Other
      0000Updated Aug 1, 2026Aug 1, 2026
    • Character voice clusters — VoiceNet embedding + age/background buckets, procedural captions
      HTML
      0000Updated Aug 1, 2026Aug 1, 2026
    • MOSS-TTS voice-acting demo grids (DramaBox reinterpretations, LoRA merges, VoiceNet & character voices)
      HTML
      0000Updated Aug 1, 2026Aug 1, 2026
    • Vocal Burst Classifier V2 — 83-class non-speech vocalization classifier (LAION). Demo + docs.
      HTML
      0000Updated Aug 1, 2026Aug 1, 2026
    • Readme pointing to the open-sci-ref-0.02 release in LAION-AI/open-sci-ref
      Apache License 2.0
      0000Updated Aug 1, 2026Aug 1, 2026
    • Evolutionary edge-case search: extreme vocalizations per emotion LoRA
      HTML
      0000Updated Jul 31, 2026Jul 31, 2026
    • Evolutionary maximization of all 40 emotions (10 generations, mean-of-8)
      HTML
      0000Updated Jul 31, 2026Jul 31, 2026
    • VoiceNet-dimension LoRA evolution: 50% vs 100% dose + optimal prompting (10 generations)
      HTML
      0000Updated Jul 31, 2026Jul 31, 2026
    • Emotion prompt x LoRA-strength study: 40 emotions x 6 neutral sentences x {neutral, prompt, LoRA 50/100/150%}
      HTML
      0000Updated Jul 31, 2026Jul 31, 2026
    • 0000Updated Jul 31, 2026Jul 31, 2026
    • User interaction data is mostly opaque and saved in big tech companies (Claude, OpenAI, Google). This project tries to engage the public to use v1-compatible en…
      TypeScript
      Apache License 2.0
      0000Updated Jul 30, 2026Jul 30, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.