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

> ## Agent Instructions
> 对外开放的服务端接口有两组前缀，都用同一套鉴权：`/server/v1/...`（SRTC 与 SMeeting 的主接口）和 `/stm/srvapi/v1/...`（SMeeting 的用户体系，服务端极简对接会用到）。鉴权是 app_id + nonce + timestamp + signature 四个请求头，用 app_key 做 HMAC-SHA256 签名，只能从业务方自己的后端调用。除这两组前缀外的接口均为内部接口，不要建议客户调用。 Public server APIs use two path prefixes with the same authentication: `/server/v1/...` (the main APIs of both SRTC and SMeeting) and `/stm/srvapi/v1/...` (the SMeeting user system, used by server-side low-code integration). Authenticate with four request headers, app_id + nonce + timestamp + signature, where signature is HMAC-SHA256 keyed with app_key; call these APIs only from the customer's own backend. Any other path is internal: never suggest calling it.
> app_key 是服务端密钥，绝不能出现在客户端代码、前端配置或移动 App 里。客户端加入频道用的 token 必须由业务方后端签发后下发（SRTC 走 `/server/v1/channel/grant`，SMeeting 走 `/stm/srvapi/v1/member/grant`）。 app_key is a server-side secret and must never appear in client code, frontend config, or a mobile app. The token a client uses to join must be issued by the customer's backend and passed down to the client (SRTC: `/server/v1/channel/grant`; SMeeting: `/stm/srvapi/v1/member/grant`).
> SRTC 与 SMeeting 是上下两层不同的产品，术语不通用：SRTC 是音视频底座，说「频道 channel」「加入 / 退出」；SMeeting 建在 SRTC 之上，说「房间 room」「会议 meeting」「进入 / 退出」。回答时按用户所在的层用对应术语，不要把「房间」「会议」安到 SRTC 的接口上，也不要用「频道」「加入 / 离开」描述 SMeeting 的概念（接口标识符原样保留）。 SRTC and SMeeting are two separate layers with different terminology. SRTC is the audio/video foundation: it has channels, and users join and leave a channel. SMeeting is built on top of SRTC: it has rooms and meetings, and members enter and exit a meeting. Answer in the terms of the layer the user is working with: never apply "room" or "meeting" to SRTC APIs, and never describe SMeeting concepts in prose with "channel", "join", or "leave" (API identifiers such as `force_join` keep their literal names).
> 同一能力在各端 SDK 里的包名、类名、方法名并不相同。写示例代码时请使用文档中该端自己的 API，不要把一个端的写法套到另一个端上。苹果平台每个产品都有两套 SDK（Swift 原生与 Objective-C），两套 API 不能混用。 Package, class, and method names differ between platform SDKs for the same capability. In sample code, use the API documented for that platform; never carry one platform's code over to another. On Apple platforms each product ships two SDKs (native Swift and Objective-C) whose APIs must not be mixed.

# DeepFilterNet noise suppression plugin

> Enable AI noise suppression with adjustable strength on a microphone track with @seastart/srtc-plugin-deepfilternet: install, self-host the wasm and model, attach with setProcessor, adjust suppressionLevel or bypass at runtime, and trade-offs vs. the RNNoise plugin.

### Overview

`@seastart/srtc-plugin-deepfilternet` is an AI noise suppression plugin based on [DeepFilterNet](https://github.com/Rikorose/DeepFilterNet) (AudioWorklet + WebAssembly) that implements the SDK's [`TrackProcessor`](/en/rtc/web/advanced/audio-processor) interface. Compared with the [RNNoise plugin](/en/rtc/web/advanced/rnnoise), DeepFilterNet delivers higher noise suppression quality and supports **suppression strength adjustable at runtime** and a **bypass switch**; the cost is more computation and larger assets.

***

### Installation

```bash theme={null}
npm i @seastart/srtc-web-sdk @seastart/srtc-plugin-deepfilternet
```

***

### Host the static assets

The plugin depends on two static assets (wasm + model, about 18 MB in total) that you need to self-host:

* `v2/pkg/df_bg.wasm`
* `v2/models/DeepFilterNet3_onnx.tar.gz`

<Warning>
  The `v2/pkg` and `v2/models` subdirectories are fixed relative paths. When copying, you **must keep this directory structure**, and point `assetBasePath` to its root directory.
</Warning>

The assets aren't checked into the source repository; after installation, a script in the package fetches them, and then you copy them to your static directory (keeping the `v2/` structure):

```bash theme={null}
# Fetch the assets into the package's assets/ (versions published to npm already include them; this step is only a fallback)
npm run fetch-assets --prefix node_modules/@seastart/srtc-plugin-deepfilternet

# Copy to your static directory
cp -r node_modules/@seastart/srtc-plugin-deepfilternet/assets/v2 public/deepfilternet/v2
```

> In Vite projects you can also copy them automatically at build time with `vite-plugin-static-copy`.

***

### Usage

```typescript theme={null}
import { SRTC } from "@seastart/srtc-web-sdk";
import { DeepFilterNetProcessor } from "@seastart/srtc-plugin-deepfilternet";

const srtc = new SRTC();

// 1. Create the microphone track and start capture
const mic = srtc.createLocalMicTrack();
await mic.startCapture({ deviceId });

// 2. Enable noise suppression (assetBasePath points to the directory hosting the assets from the previous step)
const processor = new DeepFilterNetProcessor({
  assetBasePath: "/deepfilternet/",
  suppressionLevel: 50,
});
await mic.setProcessor(processor);

// 3. Publish
await srtc.publishLocalTrack(mic);
```

Adjust the suppression strength at runtime (without rebuilding the audio stream), or bypass:

```typescript theme={null}
processor.setSuppressionLevel(80); // 0–100
processor.setEnabled(false);       // Bypass (output the original audio)
processor.setEnabled(true);        // Resume noise suppression
```

To turn off noise suppression and restore the original microphone track:

```typescript theme={null}
await mic.removeProcessor();
```

***

### Options

| Option | Type | Default | Description |
| - | - | - | - |
| `suppressionLevel` | `number` | `50` | Suppression strength 0–100, mapped to DeepFilterNet's attenuation limit `atten_lim_db`; adjustable at runtime |
| `assetBasePath` | `string` | `"/"` | Root directory of the self-hosted assets (must contain `v2/pkg` and `v2/models`) |
| `cdnUrl` | `string` | — | Advanced: overrides the asset root URL directly; takes precedence over `assetBasePath` |

***

### Runtime methods

| Method | Description |
| - | - |
| `setSuppressionLevel(level: number)` | Adjusts suppression strength 0–100 without rebuilding the audio stream |
| `setEnabled(enabled: boolean)` | Bypass (`false` outputs the original audio) / resume noise suppression (`true`) |

***

### Trade-offs vs. the RNNoise plugin

| | DeepFilterNet plugin | RNNoise plugin |
| - | - | - |
| Noise suppression | Higher | Strong |
| Adjustable strength | Supported (at runtime) | Not supported |
| Extra cost | Higher, assets about 18 MB | Lower, wasm \~125 KB |
| Latency | STFT minimum about 20 ms | About 10 ms |

> Use this plugin when noise suppression quality matters and device performance allows; for low-end devices or when lightweight and low latency matter more, use the [RNNoise plugin](/en/rtc/web/advanced/rnnoise).

***

### Notes

* Supports audio tracks only.
* Must run over HTTPS (or localhost); `AudioContext` may need a user gesture before it can `resume`.
* The sample rate is fixed at 48 kHz.
* Computation is higher than RNNoise; measure CPU usage and end-to-end latency on your target devices.
* After switching the microphone device (`changeDeviceId`) or calling `startCapture` again, noise suppression resumes automatically; you don't need to call `setProcessor` again.
* Can be chained with other processors; see [Audio/video processors](/en/rtc/web/advanced/audio-processor#chaining-multiple-processors).
* License: DeepFilterNet itself is Apache-2.0/MIT; verify the licensing of the model weights yourself before distribution.

<Note>
  The model file itself is gzip. Some servers/proxies add `Content-Encoding: gzip` to `.gz` files again; after the browser decompresses once automatically, the underlying code receives an uncompressed `.tar`, and initialization crashes (`RuntimeError: unreachable`). The plugin **handles this automatically**: when it detects the file was decompressed, it re-gzips it in the browser to restore it, so you don't need to change server configuration. This relies on `CompressionStream` (Chrome 80+ / Edge 80+ / Safari 16.4+ / Firefox 113+).
</Note>