> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.meetstream.ai/llms.txt.
> For full documentation content, see https://docs.meetstream.ai/llms-full.txt.

# Welcome to MeetStream!

[**MeetStream.ai**](http://MeetStream.ai) provides a unified API to deploy interactive bots and AI agents into meeting platforms such as Zoom, Google Meet and Microsoft Teams.

Use one integration to 

* capture media
* generate transcriptions
* interact in real-time

## Meeting Bot and Agent Features

### Core Capabilities

* Universal Integration: Connect to any major meeting platform via a single API using only the meeting URL.
* Low-Latency Media: Capture raw audio and video with \~ 200ms latency.
* Active AI Participants: Deploy bots that speak via TTS, share screens, or inject video streams.
* Managed Infrastructure: Scale from one to thousands of concurrent sessions without managing bot clusters.
* Rich Metadata: Track participant join/leave times, speaking duration, and in-meeting chat.

<CardGroup cols={2}>
  <Card title="Media Capture & Streaming" icon="duotone camera">
    - **Record:** Export mixed audio, isolated participant tracks, or composite MP4s.
    - **Stream:** Access real-time WebSocket audio (base64) and RTMP video feeds.
  </Card>

  <Card title="Transcription & Diarization" icon="duotone speaker">
    * **Live Events**: Receive webhooks for real-time speaker attribution.
    * **Post-Meeting**: Access full, speaker-labeled transcripts via the MeetStream engine or third-party providers.
  </Card>

  <Card title="Bot Interaction" icon="robot">
    * **Messaging:** Read and write in-meeting chat via API.
    * **A/V Output:** Stream live web pages, display static images, or speak using TTS.
  </Card>

  <Card title="Reliability & Management" icon="duotone sitemap">
    * **Automation:** Sync calendars for auto-dispatch and trigger auto-leave rules.
    * **Control:** Pause, resume, or mute bots mid-meeting via API.
    * **Resilience:** Built-in network auto-retries and platform consent handling.
  </Card>
</CardGroup>

## Use Cases

<Tabs>
  <Tab title="Sales AI Coaches & Agents">
    * Bot joins live calls, streams real-time attributed transcripts via WebSocket
    * NLP layer detects intent signals and objections from the live transcript stream
    * Streams live attributed transcript via WebSocket, enabling real-time coaching cues to be surfaced to the rep mid-call
    * Post-call agent auto-generates follow-up summaries and action items for rep review
  </Tab>

  <Tab title="Note Taking Agents">
    * Bot silently joins instant or scheduled meetings and transcribes with speaker diarization in real time
    * NLP pipeline extracts decisions, action items, and open questions as structured objects
    * Each action item is attributed to a speaker with source timestamp for auditability
    * Output is pushed to tools like Notion, Jira, or Confluence via API post-meeting
  </Tab>

  <Tab title="Internal Meeting Summarizers">
    * Bot captures and transcribes internal meetings across Zoom, Meet, and Teams via one API
    * On meeting end, a webhook fires the full attributed transcript to your NLP pipeline for summarisation
    * Structured summary — decisions, action items, open questions — is generated from the transcript and pushed to Slack, Notion, or email
    * Raw transcript and diarization artifact are stored and available via API for any downstream processing
  </Tab>

  <Tab title="Voice Controlled CRM Updates">
    * Bot captures the full call transcript with speaker attribution via MeetStream's API
    * Post-call, NLP layer extracts deal stage, contact details, and key notes from the transcript
    * Extracted fields are mapped and pushed to CRM objects via REST API — no manual entry
    * Works with any CRM that exposes a standard API; field mapping is configurable per org
  </Tab>
</Tabs>