Introduction
Saaya is a real-time multimodal AI agent platform. One config, every channel, voice, video, and chat, wired up with the LLMs, voices, and avatars you actually want to ship.
What is Saaya?
Saaya is the runtime that takes your AI agent from a single prompt to a production conversation. You define behaviour. We handle the parts that silently break in production, turn-taking, retrieval, media, deployment.
Every agent ships with:
- Voice, video, and chat from one config.
- Provider-agnostic language, speech, and avatar layers, switch without a rewrite.
- Retrieval over your knowledge bases, tuned per agent.
- A draft-and-publish model, so edits never reach live traffic by accident.
- Sessions you can read back: transcripts, recordings, duration, cost.
How Saaya fits
Saaya sits between your product and the conversation layer. Your code talks to the Saaya REST API; Saaya runs the agent against your callers in real time.
You define
Prompt, knowledge bases, voice, speech and listening settings.
Saaya runs
Routing, providers, turn-taking, transcripts, recordings.
You observe
Sessions, recordings, durations, costs.
Your first call
The shortest path is the single-prompt agent: create it, then edit its draft. Saaya speaks plain HTTP, so any client will do.
curl -X POST "https://api.saaya.ai/api/v1/agents/?type=single_prompt" \
-H "X-API-Key: $SAAYA_API_KEY"
curl -X PATCH https://api.saaya.ai/api/v1/agents/{agent_id} \
-H "X-API-Key: $SAAYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Pipeline Concierge",
"system_prompt": "You are Maya, a friendly inbound qualifier."
}'One header
X-API-Key. The workspace is resolved from the key, so there is nothing else to pass. See the API reference.Where to next
From here you can keep going down whichever path fits the way you build:
- Quickstart , the path from zero to a live agent, step by step.
- API reference , every endpoint, the shared envelope, and how lists paginate.
- MCP endpoint , let any MCP-compatible AI client query Saaya directly.
