# Meeting bots, recording and transcript APIs for AI agents

> 5 meeting capture & meeting infrastructure listings ranked by the Anchor benchmark. Leader Meeting BaaS (B). Services that join or record a video meeting and return the recording, transcript and summary. Meeting-bot infrastructure a developer builds on, and meeting assistants with an API or MCP server over what they captured. Compared on platforms covered, bot control, transcript access and consent handling.

- Canonical: https://www.anchorterminal.com/categories/meeting-capture
- Markdown: https://www.anchorterminal.com/categories/meeting-capture.md (~2,000 tokens)
- Slim: https://www.anchorterminal.com/categories/meeting-capture.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/meeting-capture.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-08

Services that join or record a video meeting and return the recording, transcript and summary. Meeting-bot infrastructure a developer builds on, and meeting assistants with an API or MCP server over what they captured. Compared on platforms covered, bot control, transcript access and consent handling.

- Tools ranked: 5 · agent-ready (BB or better): 0 · accept x402: 0 · hosted endpoints: 5 · desk reviews by the panel: 0
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Capabilities in this category: meetings.bot, meetings.transcript, meetings.recording, meetings.summary, meetings.calendar
- https://letme.dev/meetings.bot picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 312 | Meeting BaaS | SAS SPOKE | HTTP API | Meetings | B | 62 | medium | no | API key | hosted | none | https://www.anchorterminal.com/tools/meeting-baas.md |
| 347 | Fireflies.ai | Fireflies.AI Corp. | HTTP API | Meetings | C | 60.6 | medium | no | OAuth or key | hosted | none | https://www.anchorterminal.com/tools/fireflies.md |
| 378 | Recall.ai | Hyperdoc Inc. | HTTP API | Meetings | C | 59.5 | medium | no | OAuth or key | hosted | none | https://www.anchorterminal.com/tools/recall-ai.md |
| 512 | tl;dv | tldx Solutions GmbH | HTTP API | Meetings | D | 51 | medium | no | OAuth or key | hosted + local | none | https://www.anchorterminal.com/tools/tldv.md |
| 517 | Read AI | Read AI, Inc. | MCP server | Meetings | D | 50.4 | medium | no | OAuth | hosted | none | https://www.anchorterminal.com/tools/read-ai.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 312. Meeting BaaS, B (62)

Meeting BaaS is a hosted API from SAS SPOKE in France that sends recording bots to Zoom, Google Meet and Microsoft Teams meetings and returns recordings, transcripts and speaker data. Developers call it with an API key. A public OpenAPI 3.1 spec covers 73 v2 operations with typed errors, cursor pagination and numbered rate limits, and pricing is public per recording hour with 8 free hours. Six releases between 11 September and 6 October 2026 carried breaking changes on the live /v2 path, and no uptime SLA or security.txt was found.

- Page: https://www.anchorterminal.com/tools/meeting-baas · Markdown: https://www.anchorterminal.com/tools/meeting-baas.md · JSON: https://www.anchorterminal.com/api/v1/tools/meeting-baas.json
- Capabilities: meetings.bot, meetings.transcript, meetings.recording, meetings.calendar · endpoint: `https://api.meetingbaas.com`

### 347. Fireflies.ai, C (60.6)

Fireflies.ai is a meeting assistant that records, transcribes and summarises video meetings. An outside agent reads and manages that data through a GraphQL API and a hosted MCP server. An agent reads transcripts, summaries and analytics through a GraphQL API or a hosted MCP server with OAuth and 19 documented tools, on every plan including Free. Neither the API key nor the OAuth grant can be limited to read-only, the changelog carries no dates, and Free and Pro accounts are capped at 50 and 500 requests a day.

- Page: https://www.anchorterminal.com/tools/fireflies · Markdown: https://www.anchorterminal.com/tools/fireflies.md · JSON: https://www.anchorterminal.com/api/v1/tools/fireflies.json
- Capabilities: meetings.transcript, meetings.summary, meetings.recording, meetings.bot · endpoint: `https://api.fireflies.ai`

### 378. Recall.ai, C (59.5)

Recall.ai is a hosted API for meeting bots that join Zoom, Google Meet, Microsoft Teams and Webex calls and return recordings, transcripts and participant data. It also has calendar scheduling, desktop and mobile recording SDKs, and an MCP server. One REST call sends a bot to a meeting, with per-endpoint rate limits, `Retry-After` on 429 and 507, and idempotency keys on writes. No public status page or API changelog was found, REST API keys carry no scopes, and the hosted MCP server reads workspace data but can't create or control a bot.

- Page: https://www.anchorterminal.com/tools/recall-ai · Markdown: https://www.anchorterminal.com/tools/recall-ai.md · JSON: https://www.anchorterminal.com/api/v1/tools/recall-ai.json
- Capabilities: meetings.bot, meetings.recording, meetings.transcript, meetings.calendar, speech.diarisation, voice.streaming · endpoint: `https://us-west-2.recall.ai`

### 512. tl;dv, D (51)

tl;dv is a meeting assistant from tldx Solutions GmbH that records Google Meet, Zoom and Microsoft Teams calls and writes transcripts and notes. Agents read that library through a REST API or a hosted MCP server with five read-only tools. An outside agent can read meetings, transcripts, notes and recordings, and import media by URL, but cannot send the recorder to a call. The hosted MCP server is read-only behind OAuth with five-minute access tokens. The REST API is labelled v1alpha1, publishes no rate limits, and needs a Pro plan or higher.

- Page: https://www.anchorterminal.com/tools/tldv · Markdown: https://www.anchorterminal.com/tools/tldv.md · JSON: https://www.anchorterminal.com/api/v1/tools/tldv.json
- Capabilities: meetings.transcript, meetings.summary, meetings.recording, automation.webhooks · endpoint: `https://pasta.tldv.io`

### 517. Read AI, D (50.4)

Read AI is a meeting assistant that records Zoom, Google Meet and Microsoft Teams calls and produces transcripts, summaries and action items. Outside agents reach the reports through a remote MCP server and a REST API, both in open beta. Four MCP tools and three REST endpoints return transcripts, summaries, action items and recording links, and the MCP server can send a bot to a named meeting. Both surfaces are in open beta. Access needs a browser sign-in, access tokens last 10 minutes, and no OpenAPI file or changelog was found.

- Page: https://www.anchorterminal.com/tools/read-ai · Markdown: https://www.anchorterminal.com/tools/read-ai.md · JSON: https://www.anchorterminal.com/api/v1/tools/read-ai.json
- Capabilities: meetings.bot, meetings.transcript, meetings.summary, meetings.recording · endpoint: `https://api.read.ai/mcp`

## How we test this category

The same scripted ten-minute test meeting on Zoom, Google Meet and Microsoft Teams, captured by each listing. We check how the capture is started, the time to a transcript, speaker labels, the recording and transcript API, and what participants are told. In this run listings are graded from public evidence against the published checklist. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.