> This page is for Audio Decisions.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://dev.hume.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://dev.hume.ai/_mcp/server.

# Cookbooks

**Each cookbook is an example app in its own repository, with a guide here that walks through how it works.** Clone one to run it locally and follow along, or fork it as the starting point for your own app.

[call-01.wav](/audio-decisions/cookbooks/evaluating-many-recordings)

call-02.wav

call-03.wav

call-04.wav

Evaluating many recordings Upload a set of recordings, ask the same questions about each one and compare every answer in one table. Python SDK, Gradio

[Answering live audio Record the microphone in the browser and see answers for each 5 seconds of audio as they arrive. TypeScript SDK, Next.js](/audio-decisions/cookbooks/answering-live-audio)

## Before you start

Each cookbook assumes you know what each primitive asks and how to read its answer.

#### [Primitives](/audio-decisions/docs/primitives)

Learn what each question type asks and what its answer contains.

#### [Interpreting answers](/audio-decisions/docs/interpreting-answers)

Learn how to read each answer and set thresholds for acting on it.