Home A - Z Create page
Page Index

An Otter Wiki

Blame

7ed58c Anonymous 2026-04-17 00:32:44 1 
# Modelix
2
3
Modelix is our in-house built AI Gateway.
4
5
You can reach it at [https://10.152.0.2:9999](https://10.152.0.2:9999).
6
7
You will need an account at [https://iam.isn.edu.au](https://iam.isn.edu.au).
8
9
Once you have access, you can make a virtual key and make requests to the OpenAI-compatible API.
10
11
## Example Requests
12
13
### Chat
2feda6 Anonymous 2026-04-17 00:36:29 14
15
OpenAI API docs: [Create chat completion](https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create)
16
7ed58c Anonymous 2026-04-17 00:32:44 17
```
18
curl https://10.152.0.2:9999/v1/chat/completions -k \
19
-H "Content-Type: application/json" \
20
-H "Authorization: Bearer $VIRTUAL_KEY" \
21
-d '{
22
"model": "indra-llm/google/gemma-4-26b-a4b-it",
23
"messages": [
24
{
25
"role": "system",
26
"content": "You are a helpful assistant."
27
},
28
{
29
"role": "user",
30
"content": "Hello!"
31
}
32
]
33
}'
34
```
35
36
### Speech Generation (Text to Speech - TTS)
2feda6 Anonymous 2026-04-17 00:36:29 37
38
OpenAI API docs: [Create speech](https://developers.openai.com/api/reference/resources/audio/subresources/speech/methods/create)
39
7ed58c Anonymous 2026-04-17 00:32:44 40
```
41
curl -X POST https://10.152.0.2:9999/v1/audio/speech \
42
-k \
43
-H "Authorization: Bearer $VIRTUAL_KEY" \
44
-H "Content-Type: application/json" \
45
-d '{
46
"model": "indra-tts/default",
47
"input": "This is a text-to-speech system check. Audio synthesis is functional on Indra.",
48
"voice": "nona"
49
}' \
50
--output tts_test.wav
51
```
52
53
### Transcription (Speech to Text - STT)
2feda6 Anonymous 2026-04-17 00:36:29 54
55
OpenAI API docs: [Create transcription](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
56
7ed58c Anonymous 2026-04-17 00:32:44 57
```
58
curl https://10.152.0.2:9999/v1/audio/transcriptions \
59
-k \
60
-H "Authorization: Bearer $VIRTUAL_KEY" \
61
-H "Content-Type: multipart/form-data" \
62
-F "file=@/path/to/audio/file/on/your/computer/sample.ogg" \
63
-F "body=" \
64
-F "model=indra-stt/deepdml/faster-whisper-large-v3-turbo-ct2" \
65
-F "response_format=json"
66
```