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

# Voice & Calls

> Calls, voice agents and meeting recordings, after transcription.

Calls, voice agents and meeting recordings, after transcription. Four recipes, one per ScaleDown model.

## Compress

<Card title="Trim the backend docs down to what the question needs, so the agent can answer a live caller fast." icon="compress" href="https://scaledown.ai/cookbooks/voice-compress">
  Sits in front of your answering LLM. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | The caller is not left waiting while a big chunk of retrieved text gets processed. |
| **How it goes** | Caller asks → speech transcribed → backend pulls docs → Compress trims them → LLM writes a short answer → agent says it. |
| **Payoff** | Lower latency on the retrieval step, less token spend per answered call. |

## Summarize

<Card title="Turn a call or meeting transcript into a short recap with the decisions and action items." icon="align-left" href="https://scaledown.ai/cookbooks/voice-summarize">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Transcripts are long, conversational, and multi-speaker, exactly the workload Summarize is built for. |
| **How it goes** | Call ends → transcript in → Summarize produces the recap → push to the notetaker, CRM, or follow-up draft. |
| **Payoff** | State-of-the-art on QMSum, the meeting-summarization benchmark. |

## Extract

<Card title="Pull the CRM fields out of a sales call, deal size, economic buyer, next meeting, into clean fields." icon="magnifying-glass" href="https://scaledown.ai/cookbooks/voice-extract">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | A deal cannot move on a guess; Extract returns the numbers and names exactly as they were said on the call. |
| **How it goes** | Call ends → transcript in → you tell Extract what to look for → it returns the fields → push into HubSpot. |
| **Payoff** | Structured CRM fields straight off the transcript, no rep data entry. |

## Classify

<Card title="Send the caller to the right place based on what they say, instead of press 1 for billing." icon="tags" href="https://scaledown.ai/cookbooks/voice-classify">
  Replaces an LLM call. Open the full Python recipe.
</Card>

| | |
| - | - |
| **Why it fits** | Routing is the busiest step in the call; Classify handles a simple choice fast without paying a frontier model to overthink it. |
| **How it goes** | Caller says what they need → speech transcribed → Classify picks the label → agent routes them into that flow. |
| **Payoff** | Faster routing at lower cost per call. |


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