You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+43-11Lines changed: 43 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
-
# Setup the EchoKit server
1
+
# EchoKit Server
2
2
3
-
EchoKit Server is the central component that manages communication between the EchoKit device and AI services. It can be deployed locally or connected to preset servers, allowing developers to customize LLM endpoints, plan the LLM prompt, configure speech models, and integrate additional AI features like MCP servers.
3
+
EchoKit Server is the central component that manages communication between the [EchoKit device](https://echokit.dev/) and AI services. It can be deployed locally or connected to preset servers, allowing developers to customize LLM endpoints, plan the LLM prompt, configure speech models, and integrate additional AI features like MCP servers.
4
4
5
5
<br>
6
6
<divalign="center">
@@ -11,11 +11,43 @@ EchoKit Server is the central component that manages communication between the E
11
11
</div>
12
12
</br>
13
13
14
-
You will need an EchoKit device, or create your own ESP32 device with the [EchoKit firmware](https://github.com/second-state/echokit_box).
14
+
You will need an [EchoKit device](https://echokit.dev/), or create your own ESP32 device with the [EchoKit firmware](https://github.com/second-state/echokit_box).
15
15
16
16
17
+
## Features
17
18
18
-
## Build
19
+
EchoKit Server powers the full voice–AI interaction loop, making it easy for developers to run end-to-end speech pipelines with flexible model choices and custom integrations.
@@ -27,7 +59,7 @@ Edit `config.toml` to customize the VAD, ASR, LLM, TTS services, as well as prom
27
59
cargo build --release
28
60
```
29
61
30
-
## Configure AI services
62
+
###Configure AI services
31
63
32
64
The `config.toml` can use any combination of open-source or proprietary AI services, as long as they offer OpenAI-compatible API endpoints. Here are instructions to start open source AI servers for the EchoKit server.
33
65
@@ -40,18 +72,18 @@ Alternatively, you could use Google Gemini Live services for VAD + ASR + LLM, an
40
72
41
73
You can also [configure MCP servers](examples/gaia/mcp/config.toml) to give the EchoKit server tool use capabilities.
42
74
43
-
## Configure the voice prompt
75
+
###Configure the voice prompt
44
76
45
77
The `hello.wav` file on the server is sent to the EchoKit device when it connects. It is the voice prompt the device will say to tell the user that it is ready.
46
78
47
-
## Run the EchoKit server
79
+
###Run the EchoKit server
48
80
49
81
```
50
82
export RUST_LOG=debug
51
83
nohup target/release/echokit_server &
52
84
```
53
85
54
-
## Test on a web page
86
+
###Test on a web page
55
87
56
88
Go here: https://echokit.dev/chat/
57
89
@@ -61,7 +93,7 @@ Double click the local `index.html` file and open it in your browser.
61
93
62
94
In the web page, set the URL to your own EchoKit server address, and start chatting!
63
95
64
-
## Configure a new device
96
+
###Configure a new device
65
97
66
98
Go to web page: https://echokit.dev/setup/ and use Bluetooth to connect to the `GAIA ESP332` device.
0 commit comments