@flowingspring/dsh-voco 0.3.6 → 0.3.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -0
- package/README.zh.md +7 -1
- package/lib/client.js +546 -58
- package/lib/client.js.map +1 -1
- package/lib/plugins/voice-local.js +59 -20
- package/lib/plugins/voice-web.js +2 -1
- package/lib/plugins/voice.js +4 -0
- package/package.json +13 -3
package/README.md
CHANGED
|
@@ -38,6 +38,10 @@ Release page: [v0.3.6](https://github.com/lgquan/dsh-voco/releases/tag/v0.3.6)
|
|
|
38
38
|
|
|
39
39
|
Speech recognition requires your own [SiliconFlow API key](https://siliconflow.cn/). The only configuration name is `SILICONFLOW_API_KEY`. Speech-to-text uses SiliconFlow's currently free [`XingChenAGI/XingChenASR-V3.2-Ultra`](https://cloud.siliconflow.cn/models?target=XingChenAGI/XingChenASR-V3.2-Ultra) model; current availability and pricing are governed by the model page. Edge TTS does not require a key.
|
|
40
40
|
|
|
41
|
+
The recommended path is **Settings → Plugins → Plugin configuration** in DSH. Expand **Voice Assistant (Voco)**, enter the API key, and save. The key is stored in DSH credentials rather than the regular settings file. Start or reconnect Voice after saving.
|
|
42
|
+
|
|
43
|
+
Environment variables and `.env` remain supported for compatibility and automation.
|
|
44
|
+
|
|
41
45
|
For a temporary setting, use the same PowerShell session that starts DSH:
|
|
42
46
|
|
|
43
47
|
```powershell
|
|
@@ -78,6 +82,8 @@ dsh plugin --profile web remove @flowingspring/dsh-voco
|
|
|
78
82
|
|
|
79
83
|
Uninstalling does not delete DSH sessions or Voice history.
|
|
80
84
|
|
|
85
|
+
It also leaves a saved API key in place. To remove the key completely, delete `SILICONFLOW_API_KEY` from `refs` in `%USERPROFILE%\.dsh\.credentials.yaml` (or `$DSH_HOME/.credentials.yaml` when configured), and remove the same name from the process environment or any `.env` file.
|
|
86
|
+
|
|
81
87
|
## Features
|
|
82
88
|
|
|
83
89
|
- SiliconFlow's free [`XingChenAGI/XingChenASR-V3.2-Ultra`](https://cloud.siliconflow.cn/models?target=XingChenAGI/XingChenASR-V3.2-Ultra) cloud speech-to-text model.
|
package/README.zh.md
CHANGED
|
@@ -38,6 +38,10 @@ Release 页面：[v0.3.6](https://github.com/lgquan/dsh-voco/releases/tag/v0.3.6
|
|
|
38
38
|
|
|
39
39
|
语音识别需要你自己的[硅基流动 API Key](https://siliconflow.cn/)，配置名只有一个：`SILICONFLOW_API_KEY`。语音转文字使用硅基流动当前免费的 [`XingChenAGI/XingChenASR-V3.2-Ultra`](https://cloud.siliconflow.cn/models?target=XingChenAGI/XingChenASR-V3.2-Ultra)；免费状态和使用规则以模型页面为准。Edge TTS 不需要 API Key。
|
|
40
40
|
|
|
41
|
+
推荐在 DSH 中打开“设置 → 插件 → 插件配置”，展开“语音助手（Voco）”，填写 API Key 并保存。密钥保存在 DSH 凭据库中，不写入普通设置文件；保存后重新开启或重连语音即可生效。
|
|
42
|
+
|
|
43
|
+
环境变量和 `.env` 仍作为兼容与自动化配置方式保留。
|
|
44
|
+
|
|
41
45
|
在启动 DSH 的同一个 PowerShell 中临时设置：
|
|
42
46
|
|
|
43
47
|
```powershell
|
|
@@ -57,7 +61,7 @@ SILICONFLOW_API_KEY=sk-your-api-key
|
|
|
57
61
|
|
|
58
62
|
1. 运行 `dsh web` 并打开 DSH Web UI。
|
|
59
63
|
2. 新建或选择会话，点击麦克风并允许浏览器权限。
|
|
60
|
-
3. 直接说话，连续静音约 1.5
|
|
64
|
+
3. 直接说话，连续静音约 1.5 秒后提交一句话；也可以长按麦克风约 400 毫秒按住说话，松手后提交这一段。
|
|
61
65
|
4. 普通聊天由前台回答，需要项目工具的工作会委派给后台 Agent。
|
|
62
66
|
|
|
63
67
|
每个语音会话持续绑定自己的后台 Agent Session。上下文达到轮换阈值后，后续任务会自动进入新的子会话，但仍与原语音会话绑定。
|
|
@@ -78,6 +82,8 @@ dsh plugin --profile web remove @flowingspring/dsh-voco
|
|
|
78
82
|
|
|
79
83
|
卸载不会自动删除 DSH 会话或语音历史。
|
|
80
84
|
|
|
85
|
+
卸载也不会删除已经保存的 API Key。需要彻底清除时，从 `%USERPROFILE%\.dsh\.credentials.yaml`（设置了 `DSH_HOME` 时为 `$DSH_HOME/.credentials.yaml`）的 `refs` 下删除 `SILICONFLOW_API_KEY`，并同时清理系统环境变量或 `.env` 中的同名配置。
|
|
86
|
+
|
|
81
87
|
## 功能
|
|
82
88
|
|
|
83
89
|
- SiliconFlow 免费模型 [`XingChenAGI/XingChenASR-V3.2-Ultra`](https://cloud.siliconflow.cn/models?target=XingChenAGI/XingChenASR-V3.2-Ultra) 云端语音转文字。
|