{"slug": "agentcall-turn-any-coding-agent-into-a-live-meeting-participant", "title": "AgentCall – turn any coding agent into a live meeting participant", "summary": "AgentCall launches a tool that lets AI agents join Google Meet, Zoom, and Microsoft Teams as live participants, capable of speaking, listening, and collaborating. The platform supports voice-only, video, and screenshare modes, with real-time transcription and speaker diarization, while keeping agent intelligence running locally for privacy.", "body_md": "#\nTurn any\n\nAI agent into a\n\nmeeting\n\nteammate.\n\n**AgentCall** lets any AI agent join Google Meet, Zoom, and Microsoft Teams — speaking, listening, and collaborating like a real teammate.\n\n## One skill install.\n\nYour agent is in the meeting.\n\nInstall the skill, share your API key once, then tell your agent to join any meeting.\n\nLive in < 2 minutes### Share your\n\nAPI key.\n\nYour agent will ask for your API key the first time. Get it from [Dashboard → API Keys](https://app.agentcall.dev/api-keys). Saved once, reused across sessions.\n\n### Tell your agent\n\nto join.\n\n\"Join this meeting: https://meet.google.com/abc\" — your agent is in the call, talking, listening, and working.\n\n[Read the Blog](https://patternai.substack.com/)\n\n## Choose how your agent shows up.\n\nThree ways to participate — voice only, full video with a custom webpage as the bot's face, or audio plus screenshare.\n\n### Audio\n\nVoice-only presence. Your agent hears everything and speaks when it has something to say. Clean and lightweight.\n\nBest for: assistants, note-takers, voice agents### Webpage A/V\n\nRender a custom webpage as your bot's video feed. Avatars, live dashboards, slides — anything in HTML becomes the agent's face.\n\nBest for: branded bots, dashboards, visual displays### Webpage A/V + Screenshare\n\nAudio, video, and screenshare at once. Your agent can present slides while narrating, walk through documents, share live demos.\n\nBest for: presentations, training, live demos## Know who said what — as they say it.\n\nLive transcripts with speaker names delivered the moment words are spoken. React to the conversation in real time.\n\n**Speaker diarization**— know exactly who said what\n\n**Partial transcripts**— live updates as people speak\n\n**Full retrieval**— complete transcript after the call\n\n**Webhook or WebSocket**— your choice of delivery\n\n## Meeting awareness —\n\nyour agent stays in the loop.\n\nYour agent talks like a teammate — no commands, no syntax. It hears what is said, who said it, and what is on screen — and acts when asked, in plain English.\n\n### Listens for\n\n**Speech** Hears what each person says, transcribed live with speaker names\n\n**Who's there** Knows who joins and who leaves the meeting\n\n**Who's talking** Real-time on who's currently speaking\n\n**Chat** Reads everything posted in the meeting chat\n\n**What's on screen** Captures shared slides or content on demand\n\n### Acts on (just ask in plain English)\n\n**Speaks**\"Walk us through the Q3 numbers\" → speaks naturally with the right voice and timing\n\n**Posts chat**\"Drop the GitHub link in chat\" → posts the message\n\n**Raises a hand**\"Hold on, I want to add something\" → raises the bot's hand\n\n**Screenshares**\"Share the dashboard\" → starts a live screenshare\n\n**Shares a webpage**\"Send everyone the report\" → drops a clickable link participants open in their own browser\n\n**Shows progress** Live work-in-progress task list under its avatar while it works\n\n**Mutes**\"Mute yourself for this part\" → toggles the mic\n\n**Leaves**\"Thanks, you can drop off now\" → exits politely\n\n## Your data stays with you.\n\nYour agent's intelligence runs locally — on your machine, in your terminal or IDE. Reasoning, memory, decisions all live with you. AgentCall handles the meeting plumbing and stores nothing long-term. See our [full Privacy Policy](#privacy-policy).\n\n### Your agent runs locally.\n\nNot on our servers. Your prompts, your reasoning, your decisions — all on your machine. We never see them.\n\n### Transcripts stream in real time.\n\nDelivered to your agent over WebSocket and not permanently stored on our servers. Or skip our transcription entirely and bring your own.\n\n### We never train on your data.\n\nNot for our models, not for anyone else's. Your meetings are yours.\n\n## One skill for every platform & framework.\n\nAgentCall works with the meeting platforms your team uses, the agent frameworks developers build with, and the languages they already know.\n\n### Meeting platforms\n\n- Google Meet\n- Microsoft Teams\n- Zoom\n\n### Agent frameworks\n\n- Claude Code\n- OpenAI Codex\n- Cursor\n- Gemini CLI\n- Windsurf\n- GitHub Copilot\n- JetBrains Junie\n- OpenClaw\n\n## Localhost to meeting in seconds.\n\nYour agent builds a UI on localhost. AgentCall Tunnel makes it instantly accessible over the internet with a secure, temporary URL — and the bot loads it as its video feed.\n\n**HTTPS with wildcard TLS**— secure by default\n\n**WebSocket pass-through**— live updates supported\n\n**Random subdomain** per session — no collisions\n\n**Auto-destroyed** when the call ends\n\n**24-hour safety net**— auto-expire built in\n\n## What will your agent do in the meeting?\n\nTeams are putting AI agents to work in meetings across every department. Here are the most popular patterns.\n\n### AI agent builders & AI employees\n\nGive your agent a real seat in the meeting. Builders and AI employees use AgentCall to add voice, video, and live awareness to the agents they ship — no media stack to maintain, just an API call.\n\n### Meeting assistant & sales copilot\n\nJoins the standup or the sales call, listens in real time, answers when addressed, surfaces product data on demand, takes notes, and logs a polished summary to your CRM.\n\n### Automated presentations\n\nJoins with a slide deck as its video feed, narrates each slide via TTS, answers questions from the audience — no human presenter.\n\n### Interview bot\n\nConducts screening interviews autonomously. Asks prepared questions, listens, follows up naturally, returns a structured evaluation.\n\n### Customer support escalation\n\nJoins automatically when a ticket needs a live call. Explains the issue context and assists with troubleshooting in real time.\n\n### Multi-agent collaboration\n\nPut several agents in one meeting — one takes notes, one does lookups, one tracks action items. Independent yet coordinated.\n\n## Generous free tier.\n\nThen only what you use.\n\nSix full hours of meeting time included. After that, pay-as-you-go from $0.35/hr — or bring your own transcription and voice stack to skip those add-ons entirely.\n\n### Free trial.\n\nNo card needed.\n\nSix full hours of meeting time, every feature unlocked. Plenty of room to build, test, and ship.\n\n- 6 hours of meeting time included\n- Every mode and feature unlocked\n- No credit card required\n- Real-time transcripts, events, webhooks\n\n[Start free](https://app.agentcall.dev/login)\n\n### Pay as\n\nyou go.\n\nWhen you outgrow the free tier, pay only for the minutes your agent is actually in a call. Modular — billed per component, never bundled.\n\n- Meeting bot from $0.35/hr\n- Real-time English transcription — $0.12/hr\n- Voice intelligence — per minute\n- Text-to-speech — per generation minute\n- No subscription, ever\n\n### Bring\n\nyour own.\n\nAlready have transcription, TTS, or a voice stack you trust? Skip ours entirely. Only pay for the meeting bot.\n\n- Bring your own transcription\n- Bring your own TTS\n- Bring your own voice intelligence\n- Just pay the meeting bot rate\n\n## Common questions.\n\nStraight answers.\n\n## What is AgentCall?\n\n## Which meeting platforms are supported?\n\n## How does the agent know when to speak?\n\n`tts.speak`\n\nwith what it wants to say; the bridge handles timing. Voice intelligence waits for natural pauses, listens for the agent's name (collaborative mode), prevents barge-in by waiting for silence, and cuts the audio within ~1.5s if someone talks over the agent — tagging which sentence was interrupted so the agent can recover. You can customize the behaviour at any time by just telling the agent in plain English — wait longer before speaking, only respond when called by name, be more concise, whatever you want — the skill follows the agent's lead.## How can I make the agent respond faster?\n\n`/thinking low`\n\ngives faster responses with shallower reasoning, and `/fast`\n\n(on Opus models) speeds up output without downgrading the model. For the highest intelligence with quick response, use `/fast`\n\non Opus. Other agents (Cursor, Codex, Gemini CLI, etc.) have similar model + mode controls. The model and mode you pick determine the speed and the depth of reasoning — the skill just runs whatever your agent does.## Does it work with agent frameworks like Claude Code?\n\n## What safety features are included?\n\n## How much does it cost?\n\n## What is AgentCall Tunnel?\n\n## Turn your agent into\n\na teammate.\n\nStart building free. Your first meeting is minutes away.", "url": "https://wpnews.pro/news/agentcall-turn-any-coding-agent-into-a-live-meeting-participant", "canonical_source": "https://agentcall.dev", "published_at": "2026-07-15 03:36:34+00:00", "updated_at": "2026-07-15 04:18:07.789047+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-products", "natural-language-processing", "ai-infrastructure"], "entities": ["AgentCall", "Google Meet", "Zoom", "Microsoft Teams", "PatternAI"], "alternates": {"html": "https://wpnews.pro/news/agentcall-turn-any-coding-agent-into-a-live-meeting-participant", "markdown": "https://wpnews.pro/news/agentcall-turn-any-coding-agent-into-a-live-meeting-participant.md", "text": "https://wpnews.pro/news/agentcall-turn-any-coding-agent-into-a-live-meeting-participant.txt", "jsonld": "https://wpnews.pro/news/agentcall-turn-any-coding-agent-into-a-live-meeting-participant.jsonld"}}