Skip to content

Feature: add qwen audio live sdk - #289

Closed
songguocola wants to merge 2 commits into
dashscope:mainfrom
songguocola:feature/qwen-live-sdk
Closed

songguocola wants to merge 2 commits into
dashscope:mainfrom
songguocola:feature/qwen-live-sdk

Conversation

@songguocola

Copy link
Copy Markdown
Contributor

No description provided.

Add com.alibaba.dashscope.audio.live: QwenLiveConversation WebSocket
session with single-connect lifecycle, connection/session config
(QwenLiveConnectionParam, QwenLiveSessionConfig), client/responses
delegation, byte[] audio input, unified onError with optional ordered
async callback dispatch, and close/cancel/awaitSessionClosed semantics.

Include protocol/conversation/config/param unit tests and quick-start
and usage samples. QwenLiveConnectionParam reuses the existing
DASHSCOPE_WEBSOCKET_OMNI_BASE_URL env override.
Add an audio field to VoiceEnrollmentParam so create_voice/update_voice can
submit a base64 audio data URI (data:audio/wav;base64,...) in addition to the
existing url; validate() now accepts either url or audio. Add
createVoiceWithAudio/updateVoiceWithAudio overloads on VoiceEnrollmentService
and pass customParam.audio through the existing methods. Existing url-based
calls are unchanged. Covered by TestVoiceEnrollment.
@songguocola
songguocola deleted the feature/qwen-live-sdk branch November 10, 2026 09:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant