# n4ze3m/tiny-voca > tiny-voca is a small English text-to-speech model with two voices (F2 and M2), 4.5M parameters, trained from scratch. It runs on CPU, in PyTorch, ONNX Runtime and in the browser. - Magnitude: 6.9 out of 10 — Early signal - Stars: 466 total · +138 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 353 by evening - Star trust: star growth looks organic - Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2026-11-14 · Last push: 2026-11-15 - GitHub: https://github.com/n4ze3m/tiny-voca · Homepage: https://tiny-voca.n4ze3m.com · Page: https://gitnova.dev/en/r/n4ze3m/tiny-voca ## Useful for - Synthesize English speech from text into a WAV file on CPU - Export the model to ONNX and run it in the browser - Train your own TTS model from the open recipe and dataset ## How to get started ```sh git clone https://github.com/n4ze3m/tiny-voca.git cd tiny-voca pip install -e ".[own]" hf download n4ze3m/tiny-voca --local-dir weights export DIZIONE_DATA=weights/phonemizer ``` Copied as is from the “install” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/n4ze3m/tiny-voca#readme ## Why it’s here - Star-counter measurements on 2026-11-16 (UTC), 00:28–09:36: 328 → 466 stars (+138). This is the change over that interval. - Estimated end-of-day forecast: about +353 stars, using observed gains and the previous day. - The repository is 2 days old and already has 466 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #71. - About 55 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 55 - Issues and pull requests: 0 - Watchers: 2 - Average over the last week: 266 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 13 ## Stars per day, last 3 days (oldest → newest, today is partial) 2026-11-14 … 2026-11-16: 67, 379, 138 ## Magnitude by day, last 2 days 11-15 5.3, 11-16 6.9 ## Spotted in now - Top new repositories this week: #71 ## More in this category 1. **haziqahmedqasmi/PeakCut** — 6.6 · Early signal · Generative media · Python · +56 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 170 by evening Self-hosted Python service that turns long videos and live streams into 9:16 vertical clips with captions and a hook, using your own AI key. Aimed at streamers and editors who need to cut content. Full card: https://gitnova.dev/en/r/haziqahmedqasmi/PeakCut.md 2. **Moh4696/cinematic-skill** — 5.3 · Early signal · Generative media · Python · +41 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 105 by evening A skill for coding agents that writes, narrates and assembles a documentary film entirely from code: one continuous camera move over photos, maps and cards, timed to the voice. Every frame is drawn with Skia in Python rather than… Full card: https://gitnova.dev/en/r/Moh4696/cinematic-skill.md 3. **higurashi-ai/Haru** — 4.6 · Early signal · Generative media · Python · +38 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 98 by evening Inference code for Haru-4B, a multilingual full-duplex spoken dialogue model that listens and speaks at the same time, like on a phone call. Includes PyTorch, MLX and vLLM-Omni implementations plus a web demo. Full card: https://gitnova.dev/en/r/higurashi-ai/Haru.md 4. **TensaikunYT/Videohub** — 4.6 · Early signal · Generative media · JavaScript · +19 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 62 by evening Local review studio and render queue for videos written as code by coding agents like Claude Code or OpenCode: live preview from the film page, frame annotations, fixes and render queue. Full card: https://gitnova.dev/en/r/TensaikunYT/Videohub.md 5. **lemomo-ai/lemo-opuscar** — 4.6 · Steady · Generative media · JavaScript · +207 stars measured 2026-11-16, 00:28–09:36 UTC, ≈ 533 by evening A collection of 39 film styles, each with a reusable style prompt, a short film made entirely in code (Canvas/WebGL, TTS, ffmpeg), and DIRECTOR.md/TECHNIQUE.md guides for an AI agent director. Full card: https://gitnova.dev/en/r/lemomo-ai/lemo-opuscar.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-16 09:47 UTC, updated every 30 minutes.