* [Amical v1.12.0](https://github.com/amicalhq/amical) – AI-powered dictation and note-taking app with context-aware transcription and multi-platform support.

* [expo-speech-recognition v57.1.0](https://github.com/jamsch/expo-speech-recognition) – Cross-platform React Native speech recognition library supporting iOS, Android, and Web APIs for code reuse.

* [Deepgram JavaScript SDK v5.15.0](https://github.com/deepgram/deepgram-js-sdk) – JavaScript SDK for powering applications with advanced speech and language AI models.

* [Freestyle 0.9.2](https://github.com/freestyle-voice/freestyle) – Local-first dictation app that converts speech to text via a hotkey, with optional cloud providers, transcription cleanup, and contextual corrections.

* [Diction v14.0](https://github.com/DictionLabs/Diction) – Self-hosted Go gateway for an iOS voice and AI keyboard, streaming speech-to-text with encrypted WebSocket transport and optional cleanup.

* [TranscriptionSuite v1.3.10](https://github.com/homelab-00/TranscriptionSuite) – Fully local, private speech-to-text app with cross-platform support, speaker diarization, AI assistant, and live plus longform transcription.

* [DeLive v2.3.0-beta.2](https://github.com/XimilalaXiang/DeLive) – Desktop transcription workspace that captures system audio, routes to multiple ASR providers, and provides local-first AI review, live captions, summaries, chat, and mind maps.