Open Source TypeScript Speech to Text Software

Vibe is an open-source project by thewh1teagle designed to deliver a collaborative and interactive social application experience, though its specifics depend on its evolving community scope; its development often focuses on connecting users through dynamic features that can include chat, shared spaces, and immersive interactions. The repository typically includes backend logic, frontend integration, and real-time communication stacks to support live user engagement, performance optimizations, and modular features that adapt to social workflows. Because open-source social platforms benefit from transparency and community contribution, Vibe’s codebase allows developers to experiment with new social features, customize existing components, and build integrations with popular services for authentication, media sharing, and notifications. Projects like Vibe often emphasize scalability, responsive design, and extensibility so that communities of users can grow without major rewrites.

Handy is a free, open-source, offline speech-to-text application built for privacy, accessibility, and extensibility. Developed using Tauri (Rust + React/TypeScript), it runs natively across Windows, macOS, and Linux while performing local speech recognition without sending any audio to cloud servers. Handy allows users to start transcription instantly using a configurable keyboard shortcut—press to record, release to transcribe—and automatically pastes the resulting text into any active text field. Its backend leverages OpenAI’s Whisper models for GPU-accelerated speech recognition and Parakeet V3 for efficient CPU-only transcription with automatic language detection. To further refine accuracy and responsiveness, Handy integrates Silero’s Voice Activity Detection (VAD) for silence filtering, ensuring only speech segments are processed.

Free, open-source Opus Clip alternative for Windows. Turn long videos into platform-ready clips with local or cloud transcription, smart reframing, styled captions, and direct publishing. CLIPPING Auto: create 15s, 30s, 45s, 1m, or custom clips from the transcript Manual: click two words to set in/out points MCP: let an agent choose clips by word index with live preview Open the full GrepCut Studio editor from Clipper OVERLAYS Animated caption presets with live preview Adjust position, size, and words per line Add a logo or handle; control placement and opacity TRANSCRIPTION Run Parakeet or Whisper v3 Turbo locally, with optional MDX vocal isolation Or use your Groq/OpenRouter API key AUTOREFRAME Face and subject tracking for 9:16, 4:5, 1:1, and 16:9 Split view when two people won’t fit in one crop RENDER QUEUE Choose formats per clip Export at source quality, 1080p, or 720p PUBLISH Publish directly to TikTok and YouTube

**voconly is a free, open-source, local-first AI voice input assistant that runs entirely on your device.** It turns speech into text locally and uses AI to polish, translate, organize, and transform your words into usable content, letting you replace keyboard input with your voice in any application. No audio uploads. No cloud dependency. Your voice stays on your device. Unlike cloud-based voice input software, voconly keeps all audio data local—no uploads, no internet required, complete privacy. Powered by local AI, it combines real-time speech recognition with on-device LLM post-processing. Supports multiple ASR models (Qwen-ASR, SenseVoice, Whisper, Parakeet) and offers customizable refinement modes: auto-polishing, professional formatting, cross-language translation. Perfect for privacy-conscious users, developers, writers, and professionals handling sensitive content. If you need reliable Windows voice input without cloud dependency, voconly is your solution