Mistral Vibe
Connect Mistral Vibe to AudioLab Router.
Configuration
Install Mistral Vibe and Node.js 20 or later. Create an AudioLab workspace key with llm.write, available credits, and access to the selected model. Export it as AUDIOLAB_API_KEY in the terminal that launches the agent.
[[providers]]
name = "audiolab"
api_base = "https://api.tryaudiolab.ai/v1"
api_key_env_var = "AUDIOLAB_API_KEY"
api_style = "openai"
backend = "generic"
[[models]]
name = "openai/gpt-6-astra"
provider = "audiolab"
alias = "audiolab"
thinking = "off"
supports_images = falseAutomatic Setup
The command previews the files and fields it changes. Confirm to apply; it stores a private backup and prints an undo command. It does not store the API key or change your shell profile. Automatic file setup supports macOS and Linux.
npx https://tryaudiolab.ai/cli/router-0.1.0.tgz setup --agent vibeLaunch
npx https://tryaudiolab.ai/cli/router-0.1.0.tgz run vibeSelect the audiolab model. Vibe’s local price estimate is not a billing receipt; use Router usage for actual spend.
Supported Configuration
The recipe adds an AudioLab provider and model alias without replacing existing providers. Current Vibe supports [[models]]; configurations using a model map should be migrated with the upstream documentation instead of being rewritten by setup. Router’s usage records are the billing source; Vibe’s configured model prices are only local estimates.
Verify the Connection
Send a short text prompt, then a read-only tool request in a disposable project. Check the model, request record, and usage in Router. Test streaming and a follow-up turn before using a longer workflow. Client-specific tools and permissions remain managed by Mistral Vibe.
The setup command can check authentication and model discovery without generating a response. See the protocol contracts for model and feature limits.