Question 1

What models touch my audio and code?

Accepted Answer

OpenAI Whisper transcribes audio. GPT-4o writes summaries and distills specs, with a second verification pass that checks every requirement against the transcript. Atmos drafts code with Anthropic Claude, grounded in your repo. All via API — none of your data is used to train models.

Question 2

Does Reverbic write to my repo?

Accepted Answer

Only Atmos does, only through GitHub OAuth you connect, and generation is preview-only: nothing is committed until you review the proposed files and confirm. The output is an ordinary pull request you can reject.

Question 3

Is there an API?

Accepted Answer

The developer surface today is the CLI (curl install, pure bash) and the native MCP server at reverbic.ai/api/mcp with scoped keys. A REST API is on the roadmap.

Question 4

What does the free plan actually include?

Accepted Answer

5 spec distills, 5 hours of transcription, and 10 meetings per month, for one user — plus Context Packs and all three export formats. No credit card. The Team plan removes the caps and adds the MCP server, Coach, and up to 20 members flat.

Question 5

Where does my data live?

Accepted Answer

Postgres and S3, encrypted at rest with AES-256, TLS 1.3 in transit. Every table is row-level-security scoped to your org, so cross-tenant reads are blocked at the database layer — not in application code.

Speak it. Atmos ships it.

Async meetings → shipping pipeline.

Five ways teams actually use Reverbic.

GitHub

What it is used for

What Atmos reads

What it writes, and when