Dettivo
Get notified

§ Cloud providers

Cloud providers (BYOK)

Opt-in

Hosted STT, polish, and meeting analysis are available behind a Bring-Your-Own-Key model. OpenAI, Anthropic, or any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio, a self-hosted gateway). Keys live in Keychain. Off by default.

Who this is for

Users who want better polish or analysis quality than local MLX can deliver, users who already have an OpenAI / Anthropic account, and users running a self-hosted endpoint they want to point Dettivo at.

Three provider shapes

OpenAI hosted

Direct OpenAI account, billed by OpenAI. Keychain-stored key.

Anthropic hosted

Direct Anthropic account, billed by Anthropic. Keychain-stored key.

OpenAI-compatible endpoint

Any service that speaks the OpenAI API shape — Ollama, vLLM, LM Studio, self-hosted gateways.

Configure a hosted provider

  1. 01

    Open Settings › Models or AI Processing

    Models for STT, AI Processing for polish and analysis.

  2. 02

    Pick the provider type

    OpenAI, Anthropic, or OpenAI-compatible (Advanced Endpoint).

  3. 03

    Paste your API key

    Use the SecureField. Save stores the key in Keychain. Clear removes it.

  4. 04

    For OpenAI-compatible: set base URL + model ID

    Test Connection confirms the endpoint speaks the shape Dettivo expects.

  5. 05

    Pick the model

    The model picker pulls available models from the provider when possible.

§ Related

Launching April 2026

Be first on the launch list.

Dettivo opens for new purchases in April 2026. One-time license, three Macs, lifetime updates.