soniox

Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.

Real-time speech translation — macOS & Windows, free TTS, no server, your API keys only

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

Real-time two-way voice translator for VRChat — LLM-based, VR subtitle overlay & OSC

Dictate Wizard is an open source dictation tool powered by OpenAI's Whisper. The goal is to obsolete as much typing as possible and let you speak your emails, instant messages etc instead.

Modular audio toolkit and transcription SDK for real‑time voice applications. Works with any transcription provider, cross-platform.

跨平台桌面语音输入工具 / Cross-platform voice input app with real-time HUD, ASR, LLM correction, and text injection

Personalized Multimodal AI Agent via Google ADK & Gemini. Featuring Realtime Soniox STT, Long-term Memory (mem0), and LLM-generated Wiki Knowledge Base (inspired by Karpathy)

Fast native macOS dictation with Soniox transcription and configurable AI cleanup.

Transcribe audio from your coding agent — the Agent Skill, CLI, and SDK for OpenTranscription.

Hotkey voice typing via AI STT for Windows — talk to Claude, ChatGPT or any app with one-press send (uses AI speech-to-text models like Whisper, Soniox).

Live, translated captions for OBS Studio — powered by Soniox's real-time speech-to-text API. Pick a spoken language (with auto-detect for multilingual talks) and a caption language, and it streams translated subtitles straight into your OBS scene. Built for community centers, places of worship, and any livestream that needs live translation.

Integration for Soniox to Home Assistant.

macOS menu bar meeting recorder with Hebrew/English Soniox transcription and MCP access for agents

Hermes Agent TTS and STT plugin for AllModels speech models and voices.

Real-time translation (virtually no lag) with live captions for Even Realities G2 smart glasses, powered by Soniox

Talk on a Telegram group from Even Realities G2 smart glasses: push-to-talk voice via Soniox STT and a Telegram (GramJS) userbot. PWA-only, no server.

Soniox speech-to-text and text-to-speech for Home Assistant Assist

Free macOS dictation app with real-time Soniox streaming — bring your own API key. No subscription, no server.

Generated C# SDK for Soniox — real-time and async speech-to-text with 60+ languages, translation, speaker diarization, and language identification.