{"slug": "cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call", "title": "Cicada: Open-Source Live Subtitles, Notes, and Interpreting for Any Call", "summary": "The open-source Cicada menubar app, published under Apache-2.0 at github.com/wquguru/cicada, drew about 2,100 GitHub stars in its first week after the repository was created on November 1, 2026, according to the project's README. Cicada captures system audio from Zoom, Teams, Feishu, Google Meet, Discord, X Spaces, YouTube, Twitch and browser tabs to produce live bilingual subtitles and structured meeting notes without joining calls as a bot, running on-device ASR on Apple silicon Macs and pushing audio segments to cloud ASR on Windows, Linux and Android. The app supports macOS 14.4+, Windows 10 2004+, Ubuntu 22.04/24.04 and Android 10+, and exports notes as Markdown, Word or SRT.", "body_md": "**Cicada** — the open-source menubar app at [github.com/wquguru/cicada](https://github.com/wquguru/cicada?ref=explainx) — is climbing GitHub trending lists because it solves an annoying problem: **live bilingual subtitles and meeting notes for any audio on your computer**, without inviting a **bot** into the call. The project's README (Apache-2.0) describes capture from **Zoom, Teams, Feishu, Google Meet, Discord, X Spaces, YouTube, Twitch, and browser tabs**, then structured notes with topics, conclusions, to-dos, and glossaries.\n\nFor AI builders, Cicada is a reference stack for **voice-agent input**: on-device ASR on Apple silicon, pluggable translation backends, and a privacy posture that keeps recordings local unless you turn on sharing.\n\n## TL;DR\n\n| Question | Answer | \n|---|---|\n| License | **Apache-2.0** | \n| Platforms | **macOS 14.4+** , Windows 10 2004+, Ubuntu 22.04/24.04, Android 10+ | \n| Bot-free? | **Yes** — taps**system audio** , not a meeting participant | \n| On-device ASR | **Apple silicon Macs** (Intel/cloud needs a key) | \n| Interpreting | Hold **right Option** (Mac) for translated voice into the call | \n| Records | Local **LiveSubs** folder; export**Markdown, Word, SRT** | \n\n## Why developers noticed it now\n\nThe repository was created **November 1, 2026** and quickly accumulated **about 2,100 GitHub stars** in the first week — enough to land on trending feeds with a mature feature list (**660+ commits** on the default branch when we fetched the page). That is unusual for a solo-maintained Swift/SwiftUI Mac core with parallel **Windows, Linux, and Android** trees.\n\nThe pitch is not \"another Whisper wrapper.\" Cicada bundles:\n\n- **Live notes** with fishbone diagrams and glossary extraction while the meeting runs.\n- **Language detection within seconds** , with subtitles that fade when nobody speaks.\n- **Hold-to-talk interpreting** that routes translated speech back through the meeting mic via**BlackHole 2ch** on Mac (one-click driver install).\n- **Speaker diarization** using a bundled**WeSpeaker** voiceprint model on device.\n- **Share links** with expiry, optional passwords, and a**sensitive-content scan** before upload.\n\nThat combination maps cleanly to teams prototyping **voice agents** or **human-in-the-loop translation** without standing up a full WebRTC pipeline.\n\n## Architecture: what runs where\n\nCicada open-source live subtitles bridge system audio into bilingual meeting notes\n\nThe README's **Models** table is the cheat sheet:\n\n| Feature | With Ling API key | Without a key (Apple silicon) | \n|---|---|---|\n| Recognition | Apple on-device speech stack | Same on Apple silicon | \n| Sentence translation | **Ling-3.1-flash** (configurable) | Google Translate → Apple Translation on macOS 26 | \n| Partial-line translation | Google Translate streaming | Shows source text until sentence completes | \n| Live AI notes | Ling flash models | **Not available** without a key | \n| Interpreting TTS | Ming TTS or cloned voice sample | macOS built-in voices only | \n\n**Privacy split:** Apple silicon keeps **audio capture and recognition on laptop** for the default path. Only **text** (and short hold-to-talk clips if you configure neural voices) leaves for translation or notes. **Windows, Linux, and Android** push **audio segments** to whichever cloud ASR you configure — OpenRouter, ZenMux, self-hosted **vLLM**, **Whisper**, or **Qwen3-ASR** endpoints are explicitly named in the README as compatible examples.\n\nCicada documents **no analytics, no tracking**, and a short allowlist of network hosts (translation, your AI vendor, BlackHole download with SHA-256 check, GitHub update ping).\n\n## Permissions and the \"no bot\" tradeoff\n\nMac users grant capabilities **lazily**:\n\n| Permission | Purpose if granted | If denied | \n|---|---|---|\n| Screen & System Audio Recording | Hear meeting audio | No subtitles or notes | \n| Microphone | Room audio and interpreting | No in-room or talk-key modes | \n| Input Monitoring | Detect right **Option** hold | Pick another shortcut in Settings | \n| Admin password (once) | Install **BlackHole 2ch** virtual mic | Remote side cannot hear interpreting | \n\nLinux users should note the README warning: **notes windows remain visible in screen shares**, unlike Mac's default hidden capture. Android cannot record internal call audio — the workaround is **speakerphone + In person mode**.\n\nThese constraints matter when you compare Cicada to cloud notetakers like [Medium's AI notebook MCP](https://explainx.ai/blog/medium-tk-ai-notebook-mcp-claude-private-libraries-november-2026) or enterprise Copilot meeting features in our [Microsoft Copilot use-case guide](https://explainx.ai/blog/top-10-microsoft-copilot-use-cases-at-work-2026).\n\n## Practical setup paths\n\n**Path A — Apple silicon, zero key.** Install from [Releases](https://github.com/wquguru/cicada/releases?ref=explainx), grant system audio, use on-device recognition plus Google or Apple translation fallbacks. You get subtitles and local records, not full AI note polish.\n\n**Path B — Ling key.** Register on Ant Group's Ling platform, paste **sk-** key into Settings, unlock live notes, neural interpreting, and voice cloning from an **8–30 second** sample.\n\n**Path C — Bring your own model.** Settings supports **OpenRouter, ZenMux, OpenAI-compatible** gateways, including LAN **Ollama** or **SGLang**. README warns Windows/Linux/Android recognition latency runs **1–2 seconds behind** Ling when you switch.\n\nFor streaming ASR research complementary to this product layer, see Netease Youdao's new [Confucius4-R2T2 stable-prefix model](https://explainx.ai/blog/confucius4-r2t2-stable-prefix-streaming-asr-qwen3-voice-agents-2026) — Cicada does not ship R2T2, but voice-agent builders evaluating **non-revising transcripts** should read both posts.\n\nCicada on Apple silicon can keep speech recognition on-device for live meeting notes\n\n## Features power users care about\n\n**Word list and live correction.** Paste canonical spellings (people, codenames, product names). Cicada fixes sound-alike errors inline and supports batch **Edit line** fixes across a session with undo.\n\n**Re-listen pass on macOS 26.** Apple silicon builds can re-run on-device recognition **15–30 seconds** after each line to fix boundary typos — a nice match for [semantic caching](https://explainx.ai/blog/semantic-caching-llm-apps-cost-latency-guide-2026) thinkers optimizing double-pass workflows.\n\n**Imports and exports.** Drag local audio/video through **File → Import Recording or Video** to build bilingual records after the fact. Export paths include **Markdown, Word, and SRT** for caption pipelines.\n\n**Roadmap honesty.** The README lists missing **continuous capture of your own unmuted speech** in meetings as a top priority — today, \"you\" in the transcript mostly means **hold-to-talk** segments.\n\n## Comparison anchors\n\n| Tool | Angle | \n|---|---|\n| [Microsoft VibeVoice](https://explainx.ai/blog/microsoft-vibevoice-github-trending-open-source-voice-ai-asr-tts-realtime-mit-guide-2026) | Research models for ASR/TTS; not a menubar meeting product | \n| [Google AI Edge Foresight](https://explainx.ai/blog/google-ai-edge-foresight-mac-local-meeting-notes-embeddinggemma-2-2026) | Google demo of local notes; not cross-platform open source | \n| [Hugging Face speech-to-speech guide](https://explainx.ai/blog/huggingface-speech-to-speech-voice-agent-guide-2026) | How to wire STT→LLM→TTS for agents | \n| [Shizuku duplex voice](https://explainx.ai/blog/shizuku-duplex-japanese-full-duplex-voice-80ms-interaction-background-2026) | Research-grade full-duplex; not a shipping notes app | \n\nCicada sits closest to **daily driver productivity**: fewer benchmark charts, more permissions dialogs and hold-key muscle memory.\n\n## Security and procurement checklist\n\nTeams evaluating Cicada for **regulated** calls should read the README's sharing scanner (flags keys, unreleased financials) and remember **Share…** uploads note content to Cicada's link host — treat it like any SaaS export.\n\nFor agent builders, the relevant lesson is **data minimization**: Cicada proves many meeting-AI features only need **recognized text** leaving the device, not raw multi-hour audio — similar to how [sleep EEG consent posts](https://explainx.ai/blog/sleep-wearable-eeg-brain-foundation-models-consent-2026) discuss on-device boundaries.\n\nIf you deploy autonomous agents that summarize meetings programmatically, keep human review on outbound actions — [AgentBeam](https://agentbeam.com/?ref=explainx) is one guardrail layer when agents can send mail or patch tickets based on transcript triggers.\n\n## Android and hybrid meeting caveats\n\nAndroid builds cannot tap **in-call audio** for most meeting apps — OS policy, not a Cicada bug. The documented pattern is **speakerphone + In person mode**, which bleeds audio to the room and reduces translation quality. For confidential calls, Android may be the wrong client even though the APK exists.\n\nHybrid rooms use the same **In person** microphone path on Mac: online audio is tagged **Online**, room audio **In room**, merged into one record. macOS 14–15 behaved slightly differently (mic-only capture in some builds); read the version notes in the README before you demo to executives.\n\n## Troubleshooting installers teams hit\n\n**Mac \"Open Anyway\" gate.** Cicada admits it is **not Apple-notarized yet**. First launch requires **Privacy & Security → Open Anyway**. Security teams should plan for that friction until the roadmap notarization item ships.\n\n**BlackHole install prompt.** Hold-to-talk interpreting needs the virtual mic driver. Without admin approval once, remote participants will hear your raw language, not translated speech.\n\n**Linux screen-share visibility.** Notes windows show up in Zoom shares unless you toggle the setting — unlike Mac's default hide-from-capture behavior.\n\n**Windows SmartScreen.** README tells users to click **More info → Run anyway** — factor that into company laptop policies.\n\n## Cost modeling with third-party keys\n\nIf you skip Ling and route through **OpenRouter** or a **self-hosted vLLM** ASR endpoint, you trade **¥-priced minutes** for **token-metered** cloud bills. The README is explicit that non-Ling backends add **1–2 seconds** of subtitle lag on Windows/Linux/Android — acceptable for internal notes, painful for live interpreting.\n\nPair Cicada with our [KV cache explainer](https://explainx.ai/blog/what-is-kv-cache-llm-inference-explained-guide-2026) when you run local inference: streaming meetings generate **long contexts** if you feed full transcripts back into summarization loops.\n\n## How to try it today\n\n1. Download the latest **Release** asset for your OS from[github.com/wquguru/cicada/releases](https://github.com/wquguru/cicada/releases?ref=explainx) .\n2. Verify **SHA-256** against`checksums.txt` in the release (commands are in the README).\n3. Walk through onboarding sample audio before granting **system audio** on a live customer call.\n4. Pick **AI Service** in Settings; start without a key on Apple silicon if you only need subtitles.\n5. Read `docs/ROADMAP.md` for features still in flight before you promise executives \"full auto notes.\"\n\n## Bottom line\n\nCicada is **real software**, not a weekend demo: multi-platform clients, on-device models where Apple allows, honest key requirements elsewhere, and a no-bot capture model compliance teams may prefer. It trended because practitioners want **live AI notes** without another **meeting bot** name on the participant list.\n\nWe will update if the project ships **code signing/notarization** (on the public roadmap) or adds continuous self-speech capture in meetings.\n\n## Related reading\n\n*Version and permission details follow the Cicada README as of November 10, 2026.*", "url": "https://wpnews.pro/news/cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call", "canonical_source": "https://explainx.ai/blog/cicada-open-source-live-subtitles-meeting-notes-interpreting-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog", "published_at": "2026-11-10 00:00:00+00:00", "updated_at": "2026-11-10 00:50:36.258164+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "natural-language-processing", "ai-products", "developer-tools"], "entities": ["Cicada", "GitHub", "Zoom", "Microsoft Teams", "Google Meet", "Discord", "BlackHole 2ch", "WeSpeaker"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call", "markdown": "https://wpnews.pro/news/cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call.md", "text": "https://wpnews.pro/news/cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call.txt", "jsonld": "https://wpnews.pro/news/cicada-open-source-live-subtitles-notes-and-interpreting-for-any-call.jsonld"}}