v1.0.0
CrossMeet v1.0.0 · First stable release
CrossMeet 1.0 ships — bidirectional simul-interpret, hybrid local/cloud ASR, virtual mic output, RAG knowledge base, glossary, quick phrases, LAN API sharing. All features unlocked.
NEW
IMPROVED
CrossMeet 1.0 is here
After six months of internal development, CrossMeet 1.0 stable ships today. This is our first answer to the question "what should real-time translation actually feel like?"
Core capabilities
- Bidirectional simul-interpret — mic + system audio drive independent ASR pipelines; left/right panels separate automatically; turn-taking is instant
- Hybrid local + cloud ASR — Whisper-faster (GPU/CPU local), Whisper API, Aliyun DashScope, Qwen3-ASR — pick per scenario
- 30+ languages, any pair — Chinese, English, Japanese, Korean, German, French, Spanish, Russian, Arabic, Hindi, Vietnamese, Thai, Turkish, Polish, and more. Auto-detect + manual lock.
- Glossary management — brand names, person names, technical terms across three categories with per-meeting group activation
- Knowledge base RAG — upload PDFs / DOCX, vector retrieval injects context into prompts so the LLM speaks your business
- Virtual microphone (vMic) — TTS routes through a virtual mic device. Zoom / Teams / Discord receive native voice
- Compose Bar (simul-interpret) — type in your language, watch live translation preview, manually correct, then send (text + TTS together)
- Quick phrases — preset common phrases with one-click send + TTS playback
- History & smart export — every session auto-recorded; search, re-translate, AI summary, Markdown / PDF / DOCX export
- LAN API sharing — expose local engines (ASR / TTS / LLM) as OpenAI-compatible APIs to LAN devices
- Cloud platform presets — OpenAI, Anthropic, Aliyun, DeepSeek, SiliconFlow, Ollama, Gemini
Engineering principles
- Two iron rules — ASR source text always arrives before translation; LLM calls never block ASR output
- Minimal first install — ~80 MB installer; cloud-only users get a ~100 MB core dependency download — no GPU or multi-GB models needed
- Hardware gating + opt-in — local features auto-disable when no NVIDIA GPU is detected; local models install on demand
- Privacy-first — local-mode audio never leaves your machine; cloud requests go direct to provider, CrossMeet never proxies content
- License v2 multi-device binding — Stripe / Alipay / WeChat Pay; 2–5 device slots, hot-swappable
Known limitations
- Windows SmartScreen may show a "Windows protected your PC" warning on first install — click "More info → Run anyway"
- Local Whisper-faster recommends 6 GB+ NVIDIA VRAM; users without a GPU can rely on cloud APIs
- macOS / Linux clients planned for 2026 Q3 / Q4 respectively
See Getting Started for setup walkthrough · All releases for version history.