Home/Glossary/MIA

What is MIA?

SIGN UPALL TERMS
Sidhdharth SivasubramanianSidhdharth Sivasubramanian
Co-founder and CEO, MeetStream

MIA, the MeetStream Infrastructure Agent, is the agent layer that turns a meeting bot into a voice agent.

MIA takes the live meeting audio through an AI pipeline you configure.

It answers by voice, in chat, or with silent tool actions.

It works inside Zoom, Google Meet and Microsoft Teams.

Botper-speaker audioMIASTT, LLM, TTS or realtimeToolsMCP, functionsResponsevoice, chat, action
MIA sits on the bot: it hears, reasons, calls tools and answers inside the meeting.

How MIA works

An agent is a saved configuration you attach to any bot by its ID.

The config holds a mode, providers, a system prompt, a response modality and tools.

The bot sends per-speaker audio to the agent in under 100 milliseconds.

The agent reasons, then speaks back through the same bot.

You create it with the create agent config endpoint.

Realtime mode and pipeline mode

Two modes, and the choice is speed against control.

RealtimeOne speech-to-speech modelAround 300 milliseconds end to endOpenAI Realtime, gpt-realtime-mini bydefaultGoogle Gemini native audio, and xAIPipelineThree parts you pick yourselfSpeech to text, a language model, a voiceAround 600 to 900 millisecondsWake words and speaker-aware promptsRealtimeOne speech-to-speech modelAround 300 milliseconds end to endOpenAI Realtime, gpt-realtime-miniby defaultGoogle Gemini native audio, and xAIPipelineThree parts you pick yourselfSpeech to text, a language model, avoiceAround 600 to 900 millisecondsWake words and speaker-awareprompts
One model end to end, or three parts you pick yourself.

Pipeline mode also adds adaptive interruption handling.

Tools and responses

Agents call MCP servers and custom HTTPS functions during the conversation.

Response modeWhat the agent doesWhere it shows upVoiceSpeaks the answer aloudIn the meeting audioChatPosts the answerIn the meeting chatActionRuns the tool quietlyIn your own systemsVoiceWhat the agent does: Speaks the answeraloudWhere it shows up: In the meeting audioChatWhat the agent does: Posts the answerWhere it shows up: In the meeting chatActionWhat the agent does: Runs the tool quietlyWhere it shows up: In your own systems
The response mode decides what happens with a tool result.

Interruptions, turn detection, echo suppression and Anam avatars are settings, not code.

The voice agents page has examples.

FAQ

Frequently asked questions

What does MIA stand for?

MeetStream Infrastructure Agent.

Do I need my own model keys?

Yes, MIA is bring-your-own-key. You store provider keys in the dashboard, and MIA reads them when a session starts.

Which platforms does MIA work on?

Zoom, Google Meet and Microsoft Teams, through the same bot that records.

Can MIA run without speaking?

Yes. Chat mode responds in the meeting chat and action mode only calls tools.

Keep exploring

Voice agentsProductBridge serverGlossaryReal-time meeting agentsUse caseWebSocket streamingGlossaryMeeting botGlossaryTranscriptionIntegration

Put the vocabulary to work

One API to join, record, stream and transcribe meetings across Zoom, Google Meet and Microsoft Teams.

SIGN UPTALK TO US