> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pyai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Build with PyAI: use-case guides

> Step-by-step build guides for the products developers create on PyAI: conversation intelligence, voice dictation, AI receptionists, and call-center QA, with the exact APIs each one uses.

PyAI is an OpenAI-compatible voice AI stack: one API key covers speech-to-text
(**Hear**), text-to-speech (**Speak**), custom voices (**Clone**), the
all-in-one voice agent model (**Omni**), answering-machine detection (**AMD**),
compliance guardrails (**Trace**), and post-call summaries (**Recap**). These
guides show how to combine them into full products, with the exact endpoints,
scopes, and build order for each.

Every guide names the product category honestly, including when buying the
finished product is the right call, and links into the deep technical guides
that carry the runnable code.

## The builds

<CardGroup cols={2}>
  <Card title="Build your own Gong" href="/use-cases/build-your-own-gong">Conversation intelligence: transcribe calls, read Recap talk ratio and signals, summarize, and score eligible calls. Uses Hear, Recap, and Trace.</Card>
  <Card title="Build your own Wispr Flow" href="/use-cases/build-your-own-wispr-flow">A voice dictation app: push-to-talk mic capture, streaming partials rendered at the cursor, finals committed as you speak. Uses Hear streaming.</Card>
  <Card title="Build an AI receptionist" href="/use-cases/ai-receptionist">24/7 phone answering: greets, answers from your knowledge base, books appointments, transfers to a human. Uses Omni, telephony, and tools.</Card>
  <Card title="Build call-center QA" href="/use-cases/call-center-qa">Score eligible calls against compliance rule packs instead of manually sampling a few. Uses Trace.</Card>
</CardGroup>

## More you can build on the same APIs

* **A meeting notetaker.** Record or stream the meeting into Hear, let Recap
  write the summary and action items when it ends. Same pipeline as the
  conversation-intelligence build, pointed at meetings instead of sales calls.
* **An outbound dialer that knows when a human answers.** AMD tells you human
  vs. voicemail in a fraction of the dead-air dwell, then Omni takes the live
  ones. See the [AMD guide](/guides/amd-answering-machine-detection).
* **A voiceover studio.** Speak turns scripts into natural speech with stock or
  designed voices; [Clone](/guides/voice-cloning) enrolls a consented custom
  voice; Cast handles multi-line, expressive renders under `/v1/cast/*`.
* **An IVR replacement.** Omni answers with speech, not a phone tree, and its
  built-in call control (`transfer_to_human`, `collect`, `send_dtmf`) covers
  the routing. See the [Twilio guide](/guides/twilio-voice-agent).

## Where to start

<Steps>
  <Step title="Get an instant sandbox key">
    No signup, email, or card: `POST /v1/sandbox/keys` returns a working
    `pyai_test_` key in one curl. The [quickstart](/quickstart) has the
    copy-paste version.
  </Step>

  <Step title="Pick a build above">
    Each guide lists the exact scopes your key needs and the order to build in.
  </Step>

  <Step title="Go live on a funded key">
    Create a `pyai_live_` key in the [console](https://console.pyai.com) when
    you're ready for production traffic.
  </Step>
</Steps>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.