Qwen-LiveTranslate-Realtime AOQ access

​

Scope of Application

• Use the API Key and Workspace ID corresponding to your selected region and workspace.
• Beijing domain: {WorkspaceId}.cn-beijing.maas.aliyuncs.com; Singapore domain: {WorkspaceId}.ap-southeast-1.maas.aliyuncs.com.
• Store the API Key only on the server. Do not embed it in a browser or mobile application.
• When capturing audio with a microphone, request microphone permissions according to platform requirements.
• Download the SDK for your platform from SDK downloads.

​

Authentication and connection credentials

export ENDPOINT="{WorkspaceId}.cn-beijing.maas.aliyuncs.com"
curl -X POST \
  "https://${ENDPOINT}/api/v1/webrtc/realtime?model=qwen3.8-livetranslate-flash-realtime" \
  -H "Authorization: Bearer ${DASHSCOPE_API_KEY}" \
  -H "Content-Type: application/json" \
  -H "x-dashscope-rtc-transport: moq" \
  -d '{}'

​

Request fields

​

Response example

{
    "sid": "1d06b55683db49bba67a407902f62d02:1782706970:69aecdc5...",
    "aoqTokenForClient": "ecc1a46015d5496ca4ff7a48281eb739",
    "clientRelayEndpoints": [{"endpoint": "121.199.XX.XX", "port": 8443, "route_index": 0}],
    "clientRelayCertFingerprint": "sha256/99843495...",
    "sidExpiresInSecs": 7200,
    "extraInfo": {"workspaceIdHash": "2021b6f98cea4cff"}
}

​

Response fields

​

AOQ Client SDK connection example

let resp = try JSONDecoder().decode(AllocateResponse.self, from: responseData)

let config = AoqConnectConfig()
config.token = resp.aoqTokenForClient
config.sid = resp.sid
config.certFingerprint = resp.clientRelayCertFingerprint
config.relayEndpoints = resp.clientRelayEndpoints.enumerated().map { index, item in
    let ep = AoqRelayEndpoint()
    // Fall back to the array index when route_index is missing
    ep.routeIndex = item.routeIndex ?? index
    ep.endpoint = item.endpoint
    ep.port = item.port
    return ep
}
config.workspaceIdHash = resp.extraInfo?.workspaceIdHash ?? ""

let audioTrack = AoqTrackParam()
audioTrack.trackType = .audio
let dataTrack = AoqTrackParam()
dataTrack.trackType = .data
config.publishTracks = [audioTrack, dataTrack]
config.subscribeTracks = [audioTrack, dataTrack]

engine.connect(config)

​

Workflow

1. Obtain connection credentials through AppServer.
2. Create the SDK engine and register callbacks.
3. Configure media and Data tracks, and disable upstream media transmission.
4. Establish the AOQ connection and wait for it to connect.
5. Configure the model according to its protocol. Enable the required upstream media after confirmation.
6. Disconnect and release resources when interaction is complete.

​

1. Obtain connection credentials

​

2. Initialize the SDK and register callbacks

let createConfig = AoqCreateConfig()
createConfig.workDir = workDir
createConfig.enableDumpAudio = false
engine = AoqClientEngine.createEngine(createConfig, delegate: self)

​

3. Configure the SDK

​

Select media directions

​

Media directions for this model

​

Configure media parameters and tracks

engine.enableSendMediaStream(.audio, enable: false)

​

4. Establish Connection

engine.connect(connectConfig)

​

5. Exchange model events and media

​

Send and parse model events

// Build eventJSON according to the target model client event protocol.
let msg = AoqDataMsg()
msg.data = eventJSON.data(using: .utf8)!
engine.send(msg)

​

Enable media after the model is ready

engine.enableSendMediaStream(.audio, enable: true)

​

6. End interaction and release resources

1. Stop capturing and disable upstream audio; cease sending input, and send one session.finish message via the Data track.
2. Maintain the AOQ connection, Data subscription, and audio playback, continue receiving the original text, translation, and translated audio of the final sentence, and wait for session.finished.
3. If full playback of the translated audio is required, disconnect the connection and release resources only after finishing local audio playback cleanup.

engine.disconnect()
AoqClientEngine.destroy()

​

Sending and Receiving Events via the Data Channel

• Use the type field of events to identify model events, and handle associated identifiers according to this model’s event reference.
• Operations such as initialization confirmation, input submission, response cancellation, and task completion—required by the model—are all handled within the Data channel according to the corresponding protocol; these constitute the model’s interaction semantics and are distinct from disconnecting the transport connection.
• Before ending, complete input submission and result reception as described in this model’s event documentation; if full playback is required, release the connection only after processing any locally queued audio.
• Media data is transmitted via media tracks. When referencing the model event documentation, the media encapsulation and available interaction modes still follow the access method described in this document and do not directly adopt WebSocket's media transmission approach.

​

Advanced features

​

Session Configuration Example

{
  "type": "session.update",
  "session": {
    "output_modalities": [
      "text",
      "audio"
    ],
    "audio": {
      "input": {
        "turn_detection": {
          "type": "speaker_detection",
          "threshold": 0.5
        }
      }
    },
    "translation": {
      "language": "en"
    }
  }
}

​

AOQ SDK downloads

​

Event references

• Client events
• Server-Side Events

​

Scenario Tutorials

• Use AOQ to access qwen3.8-livetranslate-flash-realtime for real-time speech translation