dsh-live-voice

DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn 适合需要测试或使用DSH实时语音交互及Qwen语音端点的用户。

Package

dsh-live-voice

Compatibility

Unverified

Harness peer range

^0.1.1-rc.1 || 0.1.2-alpha.1 || 0.1.2-alpha.2 || 0.1.2-alpha.3

Cordis peer range

>=4.0.1 <5

Version

0.3.0-preview.5

License

MIT

Last updated

Sep 5, 2026

Development configuration

The bundle inserts the compatibility-stable guarded-live-voice Cordis row with the dsh-live-voice package name and explicit synthetic-demo provider. To use Qwen, a profile override must select qwen and provide an Alibaba Cloud Model Studio workspace id before provider authorization:

- id: guarded-live-voice
  name: dsh-live-voice
  config:
    provider: qwen
    credentialRef: DASHSCOPE_API_KEY
    dashscopeWorkspaceId: your-workspace-id
    model: qwen-audio-3.0-realtime-plus
    route: /guarded-voice
    trustedHosts: localhost,127.0.0.1,[::1]
    maxConnections: 8

After accepted disclosure, the preview opens the allowlisted Qwen endpoint for one exact-session manual turn and resolves the credential only on the Host. A second explicit button starts browser capture; finishing it commits only that bounded provider turn. This path is fake-tested but still needs a packaged served-Web shell receipt and credential-backed Qwen roundtrip. The separate file:// + IPC Desktop carrier requires issue #20 first.

Configure the credential through DSH's credential provider. Never put a secret value in cordis.patch.yml, browser storage, an issue, or a log.

dsh-live-voice

Other repositories with this package name

Install

README

Development configuration