ThreadCast — Neural Models Mirror
Threads, now a podcast.
threadcast.app · pixellabs.ventures
Self-hosted mirror of the on-device neural TTS models used by ThreadCast across both shipping platforms — the Chrome extension and the Android app. Three engine families on Android (Piper VITS, MeloTTS English VITS2+BERT, Kokoro StyleTTS2), two on the extension, one source of truth.
This repository exists so each platform can ship a stable, version-pinned set of model weights without depending on the availability or rate-limits of upstream Hugging Face repos at runtime.
Note: if you're a ThreadCast user, you don't need anything here — the extension and the Android app each download (or bundle) what they need automatically. This page is for transparency, contributors, and forks.
Repository layout
threadcast-neural-models/
├── extension/ ← Chrome extension — raw files, lazy-fetched
│ ├── neural-28m/ Piper VITS — 5 voices, raw HF format (Lite tier)
│ ├── neural-melo-en/ MeloTTS English VITS2+BERT — 5 EN accents (GPU Lite tier)
│ └── neural-82m/ Kokoro StyleTTS2 — 1 model + 11 voice embeddings (Studio tier)
│
└── mobile-android/ ← Android app — production zips fetched at runtime
└── v1/ 10 zips: 1 shared espeak + 5 per-voice Piper
+ 2 MeloTTS (v2 current "Local AI Plus" + v1 rollback reference)
+ 1 KittenTTS-nano ("Local AI Plus" legacy — v1.1.x cached installs only)
+ 1 Kokoro ("Local AI Studio")
Two of the ten are kept-but-not-fetched; see the
mobile-android sub-README for the retention table.
| Subtree | Format | Consumed by | Sub-README |
|---|---|---|---|
extension/ |
Raw HF (per-file .onnx, .bin, tokenizer.json) |
Chrome extension via @huggingface/transformers + @realtimex/piper-tts-web |
extension/README.md |
mobile-android/ |
ZIP archives, sherpa-onnx packaging | Android app at runtime via AssetInstaller.kt — first-launch download with cancel/delete | mobile-android/README.md |
The two subtrees parallel each other where they overlap — same Piper, MeloTTS, and Kokoro engine families, just packaged for each platform's runtime. The extension fetches raw .onnx / .txt files lazily and runs them via onnxruntime-web; Android downloads pre-packaged zips and extracts via sherpa-onnx native. Same engine weights on both surfaces, different ONNX runtime.
Engines at a glance
| Engine | Architecture | Params | Per-voice cost | Quality tier |
|---|---|---|---|---|
neural-28m |
Piper VITS | ~28 M | One ONNX file per voice (~63 MB) | Standard — fast, CPU-friendly, single-thread WASM real-time on a laptop. Surfaced on Android as Local AI Lite, on the extension as AI Neural CPU. |
neural-52m |
MeloTTS English (VITS2 + BERT prosody assist) | ~52 M | Single ONNX model + CMUdict lexicon. Android: fp16 ( |
Sweet spot — five English accents (US / UK / Indian / Australian / Default) with speaker-id switching at synth time. BERT-conditioned prosody gives noticeably more natural intonation than Piper. Surfaced on Android as Local AI Plus (sherpa-onnx CPU, fp16) and on the extension as Neural · GPU Lite (ORT-Web WebGPU, fp32) — one engine family, surface-appropriate tier name on each. |
neural-15m |
KittenTTS-nano VITS | ~15 M | Single fp16 model + 8 speaker embeddings (one ~26 MB file serves all) | Legacy — was Local AI Plus in ThreadCast v1.1.x. Replaced by MeloTTS in v1.2.0. Kept in this mirror so users with existing v1.1.x installs retain a working fallback if MeloTTS load fails mid-thread. |
neural-82m |
Kokoro StyleTTS2 | ~82 M | Single model + 256-dim style vectors per voice (one ~150 MB file serves all 11) | Premium — more natural prosody, GPU-accelerated on Chrome (WebGPU); CPU-only on Android (perf-gated). Surfaced on Android as Local AI Studio, on the extension as AI Neural GPU. |
License
This repository mirrors upstream models for distribution stability. Each upstream project retains its own license:
- Kokoro-82M: Apache-2.0 (upstream model card)
- MeloTTS English: MIT (upstream repo)
- KittenTTS-nano (v0.1): Apache-2.0 (upstream model card)
- Piper voices: MIT, with individual voice attributions in each
.onnx.json - transformers.js, onnxruntime-web, onnxruntime-android: Apache-2.0
- sherpa-onnx: Apache-2.0
The mirror layout, READMEs, and any custom additions in this repository are licensed under MIT by Pixel Labs.
Links
- 🌐 ThreadCast: threadcast.app
- 🧑💻 Pixel Labs: pixellabs.ventures
- 🐦 Issues / questions: open an issue on the ThreadCast extension repo