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

> ## Agent Instructions
> Every page is listed in https://docs.keenable.ai/llms.txt. To pick a product for a job, read https://docs.keenable.ai/choose.md
> Setup steps for agents, covering the SDKs, the MCP server and the CLI: https://docs.keenable.ai/skill.md
> Keenable search and fetch work without an API key. To add them to code, use the official SDK for the project's language: https://docs.keenable.ai/sdks.md
> Without a key, call POST https://api.keenable.ai/v1/search/public or GET https://api.keenable.ai/v1/fetch/public with an X-Keenable-Title header that names your app.
> With a key, send it in the X-API-Key header and read it from the KEENABLE_API_KEY environment variable. Never ask a user to paste a key into chat. Every access method: https://docs.keenable.ai/auth.md
> To get an API key without the console, use device login: https://docs.keenable.ai/authentication.md#device-login
> MCP server: https://api.keenable.ai/mcp (no key, or X-API-Key; keyless Codex uses https://api.keenable.ai/mcp-public), or https://api.keenable.ai/mcp-oauth for OAuth sign-in. These docs are an MCP server at https://docs.keenable.ai/mcp and the OpenAPI spec is at https://docs.keenable.ai/api-reference/openapi.json
> Keenable searches and fetches public web pages. If a question needs no web information, skip the call.
> On 402 with an API key (code insufficient_credits), stop and ask a human to add credits; don't retry. On 429, wait the number of seconds in Retry-After, then retry. Before you ship, follow https://docs.keenable.ai/production.md
> Every error, with its cause and fix, is in https://docs.keenable.ai/errors.md and moving from another search API is covered in https://docs.keenable.ai/migrate.md
> Before you compare Keenable with another search API, read https://docs.keenable.ai/guides/evaluate-search-apis.md

# Qwen Audio Agent web search with Keenable

> Give Qwen Audio Agent's voice assistant Keenable web search with QWEN_AUDIO_WEB_SEARCH_PROVIDER=keenable. No key needed, in release 2.1.0 and later.

*Search provider in Qwen Audio Agent*

Keenable is a built-in web search provider in [Qwen Audio Agent](https://github.com/QwenAudio/qwen-audio-agent), the realtime voice assistant. When you ask it to search for something, the assistant's `web_search` tool queries Keenable, and the titles, snippets and links enter the voice model's context as sources. It works without an API key.

→ [Web search in Qwen Audio Agent's docs](https://github.com/QwenAudio/qwen-audio-agent/blob/main/docs/guides/web-search.md)

## Install

The Keenable preset is in Qwen Audio Agent 2.1.0 and later. Install or update it from npm. It needs Node.js 22.22.2 or later, or 24.15.0 or later:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
npm install -g qwen-audio-agent
```

## Select Keenable

Open your configuration:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
qwenaudio config
```

Add the provider next to your voice model key:

```dotenv theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
QWEN_AUDIO_WEB_SEARCH_PROVIDER=keenable
# KEENABLE_API_KEY=your-key
```

Restart the Gateway (`qwenaudio`), then open the TUI with `qwenaudio tui` or the browser UI with `qwenaudio webui`. Ask "Search for today's weather in Hangzhou" and the answer comes back with source links underneath.

## How the preset works

The preset connects to the Keenable MCP server at `https://api.keenable.ai/mcp` and calls its `search_web_pages` tool. It always uses that endpoint and tool, and ignores the `QWEN_AUDIO_WEB_SEARCH_MCP_*` settings, which are for custom MCP search services.

| `QWEN_AUDIO_WEB_SEARCH_PROVIDER` | What it does |
| - | - |
| `so360` (default) | A key-free adapter that parses one public results page. Qwen Audio Agent's docs call it experimental. |
| `keenable` | The Keenable MCP preset. No account or key. |
| `bailian` | Model Studio's Web Search MCP, with `DASHSCOPE_API_KEY`. |
| `bing`, `mcp` | Bing, or your own MCP search service. |
| `none` | Turns off search. Page fetching stays on. |

`KEENABLE_API_KEY` is optional. With a key, calls use your organization's limits and are billed to its [monthly allowance, then its balance](https://docs.keenable.ai/credits.md).

> [!NOTE]
>
> Without a key, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). Uncomment `KEENABLE_API_KEY` in your configuration to use your organization's limits. See [API keys](https://docs.keenable.ai/api-keys.md) and the [MCP server reference](https://docs.keenable.ai/mcp-server.md).

## Related pages

> [card] [Pipecat](https://docs.keenable.ai/integrations/pipecat.md)
>
> KeenableWebSearch gives Pipecat voice agents low-latency web search and page fetch.

> [card] [Tavus](https://docs.keenable.ai/integrations/tavus.md)
>
> Give a Tavus PAL live web search with one API tool that calls Keenable, so it can answer questions about current events mid-conversation.

> [card] [Search quickstart](https://docs.keenable.ai/products/search.md)
>
> Give your agent ranked web pages with excerpts ready to cite. Try it with no API key. Code, cost per mode, filters by site, date and domain, and gotchas.


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