nova-audio-agent 0.1.1 → 0.1.2
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 +82 -13
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,24 +1,93 @@
|
|
|
1
|
-
# Nova Audio Agent
|
|
1
|
+
# Nova Audio Agent
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
**An always-on voice agent with restrained proactivity and voice-controlled workspaces.**
|
|
4
|
+
|
|
5
|
+
[GitHub](https://github.com/deepnovacore/NovaAudioAgent) ·
|
|
6
|
+
[简体中文](https://github.com/deepnovacore/NovaAudioAgent/blob/main/README.zh-CN.md) ·
|
|
7
|
+
[Watch the demo (Chinese)](https://youtu.be/t1c-2O-QsxE) ·
|
|
8
|
+
[Desktop downloads](https://github.com/deepnovacore/NovaAudioAgent/releases)
|
|
9
|
+
|
|
10
|
+
Nova (小诺) keeps a conversation going while longer tasks run in the background.
|
|
11
|
+
It is designed to report useful milestones, clarify requests, and let you steer
|
|
12
|
+
work through voice without narrating every small step.
|
|
13
|
+
|
|
14
|
+
This npm package provides the `novaaudio` command to install and launch the
|
|
15
|
+
desktop application. You do not need to clone or build the repository to use it.
|
|
16
|
+
|
|
17
|
+
## Get started
|
|
18
|
+
|
|
19
|
+
Requirements: **Node.js 22.13.0 or newer**, npm, and **macOS on Apple Silicon**
|
|
20
|
+
or **Windows x64**. The first launch needs access to GitHub to download the app.
|
|
4
21
|
|
|
5
22
|
```bash
|
|
6
|
-
npm install
|
|
23
|
+
npm install --global nova-audio-agent
|
|
24
|
+
novaaudio config
|
|
7
25
|
```
|
|
8
26
|
|
|
9
|
-
|
|
27
|
+
In the desktop settings, configure your [DashScope](https://platform.qianwenai.com)
|
|
28
|
+
API key for the default Qwen realtime voice service and your
|
|
29
|
+
[Tavily](https://docs.tavily.com) API key for web search. For coding tasks, set up
|
|
30
|
+
a logged-in Codex executable; see the
|
|
31
|
+
[setup guide](https://github.com/deepnovacore/NovaAudioAgent/blob/main/docs/getting-started.md).
|
|
32
|
+
Allow microphone access when prompted, then launch Nova:
|
|
10
33
|
|
|
11
34
|
```bash
|
|
12
35
|
novaaudio
|
|
13
|
-
novaaudio config
|
|
14
|
-
novaaudio doctor
|
|
15
36
|
```
|
|
16
37
|
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
|
|
38
|
+
Hover over the desktop orb to access its controls. Open settings again with
|
|
39
|
+
`novaaudio config`, or inspect your local setup with `novaaudio doctor`.
|
|
40
|
+
|
|
41
|
+
## Why Nova?
|
|
42
|
+
|
|
43
|
+
- **Talk while work continues.** Long-running tasks execute in the background
|
|
44
|
+
while Nova stays available for conversation.
|
|
45
|
+
- **Progress worth hearing.** Restrained proactivity aims to surface meaningful
|
|
46
|
+
updates without reading out every coding event.
|
|
47
|
+
- **Manage workspaces by voice.** Create or switch workspaces and sessions
|
|
48
|
+
through proposals that you confirm.
|
|
49
|
+
- **Steer ongoing work.** The Codex integration uses its native app-server
|
|
50
|
+
transport to support real-time steering.
|
|
51
|
+
|
|
52
|
+
The repository also documents ongoing development. Features and acceptance
|
|
53
|
+
status on development branches may differ from the shipped desktop release;
|
|
54
|
+
check the [release notes](https://github.com/deepnovacore/NovaAudioAgent/releases)
|
|
55
|
+
for your installed version.
|
|
56
|
+
|
|
57
|
+
## Commands
|
|
58
|
+
|
|
59
|
+
| Command | What it does |
|
|
60
|
+
| --- | --- |
|
|
61
|
+
| `novaaudio` or `novaaudio start` | Download the desktop app if needed, then launch it |
|
|
62
|
+
| `novaaudio config` | Download the app if needed, then open its settings |
|
|
63
|
+
| `novaaudio doctor` | Inspect platform support, local installation, and configuration status |
|
|
64
|
+
| `novaaudio --version` | Print the desktop release version used by the CLI |
|
|
65
|
+
| `novaaudio --help` | Show command help |
|
|
66
|
+
|
|
67
|
+
## Installation details
|
|
68
|
+
|
|
69
|
+
The CLI downloads the matching `v0.1.1` desktop release from
|
|
70
|
+
[GitHub Releases](https://github.com/deepnovacore/NovaAudioAgent/releases/tag/v0.1.1)
|
|
71
|
+
into `~/.nova-audio-agent/cli/releases/` and verifies its published SHA-256 digest
|
|
72
|
+
before launching it. It reuses the desktop client's encrypted settings store;
|
|
73
|
+
the CLI does not read or print secret values.
|
|
74
|
+
|
|
75
|
+
Documentation-only npm updates may have a newer package version while retaining
|
|
76
|
+
the same desktop release. `novaaudio --version` continues to report `0.1.1`.
|
|
77
|
+
|
|
78
|
+
This release supports macOS arm64 and Windows x64. Linux and Intel Mac desktop
|
|
79
|
+
downloads are not included. The desktop application is currently unsigned, so
|
|
80
|
+
macOS Gatekeeper or Windows SmartScreen may display a security warning.
|
|
81
|
+
|
|
82
|
+
## Learn more
|
|
83
|
+
|
|
84
|
+
- [Getting started and integrations](https://github.com/deepnovacore/NovaAudioAgent/blob/main/docs/getting-started.md)
|
|
85
|
+
- [Runtime architecture](https://github.com/deepnovacore/NovaAudioAgent/blob/main/docs/architecture.md)
|
|
86
|
+
- [Design: when should a proactive voice agent speak?](https://github.com/deepnovacore/NovaAudioAgent/blob/main/docs/blog/2026-08-proactive-voice-agent-design-space.md)
|
|
87
|
+
- [Report an issue](https://github.com/deepnovacore/NovaAudioAgent/issues)
|
|
88
|
+
- [Build from source and contribute](https://github.com/deepnovacore/NovaAudioAgent/blob/main/CONTRIBUTING.md)
|
|
89
|
+
|
|
90
|
+
## License
|
|
21
91
|
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
show a security warning.
|
|
92
|
+
Copyright 2026 DeepNovaCore.
|
|
93
|
+
[Apache License 2.0](https://github.com/deepnovacore/NovaAudioAgent/blob/main/LICENSE).
|