# zephyr4123/speakmore

> Free voice input app for macOS and Windows: press a hotkey, dictate, and the transcribed text is inserted at the cursor. Supports cloud models (Gemini, OpenAI, Qwen, DeepSeek and others) as well as a fully local mode with no data upload.

- Magnitude: 2.2 out of 10 — Early signal
- Stars: 100 total · +1 star measured 2026-10-19, 04:56–06:22 UTC, ≈ 10 by evening
- Star trust: star growth looks organic
- Category: Productivity & self-hosted · Language: JavaScript · License: MIT · Created: 2026-10-13 · Last push: 2026-10-19
- GitHub: https://github.com/zephyr4123/speakmore · Homepage: https://speakmore.zephyrxiang.com · Page: https://gitnova.dev/en/r/zephyr4123/speakmore

## Useful for

- Dictate text into any input field instead of typing
- Set up local speech recognition without sending audio to the cloud
- Connect your own OpenAI-compatible API key for transcription and cleanup

## Why it’s here

- Star-counter measurements on 2026-10-19 (UTC), 04:56–06:22: 99 → 100 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +10 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 100 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #199.
- About 5 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: 31
- Issues and pull requests: 9
- Watchers: 1
- Average over the last week: 16 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-13 … 2026-10-19: 0, 0, 9, 60, 16, 16, 1

## Spotted in now

- Top new repositories this week: #199

## Similar by description

1. **isair/jarvis** — 1.6 · Steady · AI agents · Python · +6 stars measured 2026-10-19, 00:13–06:24 UTC, ≈ 15 by evening
   A private local-first desktop voice assistant: speech recognition, LLMs and speech synthesis run on your own hardware via Ollama or OpenAI-compatible servers, with personal memory and MCP tools.
   Full card: https://gitnova.dev/en/r/isair/jarvis.md
2. **watzon/sayso** — 1.1 · Quiet · Apps · Rust · +1 star measured 2026-10-19, 00:14–06:25 UTC, ≈ 3 by evening
   A cross-platform dictation app for macOS, Windows and Linux that runs speech-to-text locally: press a hotkey, speak, and the text is pasted into the focused application.
   Full card: https://gitnova.dev/en/r/watzon/sayso.md
3. **jamiepine/voicebox** — 2.9 · Steady · Generative media · Python · +16 stars measured 2026-10-19, 00:07–06:20 UTC, ≈ 71 by evening
   A local-first AI voice studio: clone voices, generate speech with 7 TTS engines, and dictate into any app via a global hotkey. An open-source alternative to ElevenLabs and WisprFlow running entirely on your machine.
   Full card: https://gitnova.dev/en/r/jamiepine/voicebox.md
4. **opennookorg/betterwispr** — 1.6 · Cooling · Apps · Swift · +0 stars measured 2026-10-19, 00:10–06:23 UTC, ≈ 3 by evening
   Local-first macOS dictation app: hold a shortcut, speak, and transcribed text is pasted into any app using on-device Whisper, Parakeet or Apple speech. Positions itself as a free, open-source offline alternative to Wispr Flow.
   Full card: https://gitnova.dev/en/r/opennookorg/betterwispr.md
5. **tlack/babytalk** — 0.2 · Steady · Hardware, IoT & robotics · C · +0 stars measured 2026-10-19, 00:14–06:27 UTC, ≈ 0 by evening
   Fully offline speech-to-text and text-to-speech for ESP32-S3/P4 in C, MicroPython and AtomVM, with STT/TTS models and a data generation and finetuning framework.
   Full card: https://gitnova.dev/en/r/tlack/babytalk.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 2026-10-19 06:29 UTC, updated every 30 minutes.