Sawalni API
Put Sawalni in your app.
Use a familiar chat API to build assistants that understand multilingual conversation, images, audio, and your product’s tools. Start with one request. Keep control of the experience.
Already using an OpenAI-style chat client? Set a new base URL, key, and model ID.
from openai import OpenAI
client = OpenAI(
base_url="https://api.sawalni.com/v1",
api_key="YOUR_API_KEY"
)
reply = client.chat.completions.create(
model="sawalni-beta",
messages=[dict(role="user", content="سلام!")]
)Why Sawalni
Your product, in their language.
Sawalni is built from Morocco for Darija, Amazigh, Arabic, and multilingual use. It can follow a conversation, work with visual and audio input, and call tools you define.
Evaluate it on your own tasks before replacing another model. The integration is familiar; model behavior depends on the workload.
Explore the model and demos →
Explain what happens in this video.
Three video frames · input to Sawalniفالفيديو، واحد السيد واقف فواحد السوق، كيشوف فواحد الحيط عامر بحوايج ديال الجلد، قرون، و حوايج خرين. ف اللقطة اللولة، كيدوز يدو على شي حاجة ديال الجلد. ف اللقطة التانية، كيهز واحد القرن كبير. ف اللقطة التالتة، كيشوف مزيان ف القرن و كيتحرك شوية.
Recorded Sawalni API output · source video: IMAD EL MAADI / Pexels
Where it fits
Start with a real job.
Customer support
Answer questions in the language your customers use. Connect your own knowledge and actions when the workflow needs them.
See Sawalni Batbot →In-app assistant
Add chat to an existing product. Let people ask, refine, and complete everyday tasks with your tools.
See a tool-use demo →Multimodal intake
Accept text, images, audio, or sampled video frames in a conversation, then return a useful answer or structured result.
See recorded inputs →Build with Sawalni
One model. Your application.
Create an API key, read the docs, and test a task from your own product.