> 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.

# Changelog

## November 16, 2026

## Faster responses

**A decisions request now returns in about half the time.** With [live audio](/audio-decisions/docs/preparing-your-audio#live-audio), each answer arrives closer to the moment it describes, and you can send clips more often. The table shows the median time for three requests.

<table>
  <thead>
    <tr>
      <th>
        Audio
      </th>

      <th>
        Questions
      </th>

      <th>
        Before
      </th>

      <th>
        Now
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        10 seconds
      </td>

      <td>
        1
      </td>

      <td>
        72 ms
      </td>

      <td>
        42 ms
      </td>
    </tr>

    <tr>
      <td>
        10 seconds
      </td>

      <td>
        4
      </td>

      <td>
        117 ms
      </td>

      <td>
        51 ms
      </td>
    </tr>

    <tr>
      <td>
        60 seconds
      </td>

      <td>
        4
      </td>

      <td>
        234 ms
      </td>

      <td>
        119 ms
      </td>
    </tr>
  </tbody>
</table>

## November 7, 2026

## Shorter audio

**A request now takes audio from 1 second long, down from 5 seconds.** Audio under 1 second is rejected with `audio_too_short`, and [`POST /v0/decisions/file/input_tokens`](/audio-decisions/reference/decisions/input-tokens) accepts an `audio_duration_ms` of 1,000 or more. Most questions still give better answers with 5 seconds or more: each [use case](/audio-decisions/docs/use-cases) now shows the shortest audio it holds up on. See [Limits](/audio-decisions/docs/limits#audio).

## November 6, 2026

## Higher rate limit

**Each organization can now send 600 requests per minute, up from 60.** The limit still counts requests to every Audio Decisions endpoint over a sliding 60-second window and is shared by every API key in the organization. See [Limits](/audio-decisions/docs/limits#rate-limits).

## November 2, 2026

## Audio Decisions API launch

**The Audio Decisions API is now available.** Send an audio file with questions written in plain language, and get back probabilities that your code can threshold, rank or combine. Start with the [overview](/audio-decisions/docs/overview).

* **Decisions endpoint.** [`POST /v0/decisions/file`](/audio-decisions/reference/decisions/create) answers your questions about one audio file in one request. Each question has one of four [primitives](/audio-decisions/docs/primitives), `noul`, `choice`, `score` or `span`, which sets what its answer describes.
* **Input tokens endpoint.** [`POST /v0/decisions/file/input_tokens`](/audio-decisions/reference/decisions/input-tokens) estimates the input tokens of a decisions request. See [Billing](/audio-decisions/docs/billing).
* **Run endpoints.** [Runs](/audio-decisions/docs/runs) return the status, timing, audio size and request of each past decisions request.
* **SDKs.** Python (`hume-audio-decisions`) and TypeScript (`@humeai/audio-decisions`) SDKs cover every endpoint. See the [Python quickstart](/audio-decisions/docs/quickstart/python) and the [TypeScript quickstart](/audio-decisions/docs/quickstart/typescript).