Sign up and log in
Create an account at app.osvi.ai using your email or Google. If your organisation already uses OSVI, ask an admin to invite you instead so you join the existing workspace.
Create an agent
Go to Agents and click Create Agent. You’ll choose:
- Agent mode — Voice Agent (phone and web calls) or Chat Agent (text conversations). Pick Voice Agent for this guide.
- Prompt structure — Single Prompt (one system prompt drives the whole conversation) or Multi Prompt (a graph of prompts for branching flows). Start with Single Prompt.
- A name and optional description.
Write the prompt
On the agent’s Agent tab, set two things:The prompt writing guide covers this in depth — it’s the single highest-leverage thing you can read.
- First message — what the agent says when the call connects. Leave it empty to have the agent wait for the other person to speak first.
- System prompt — the agent’s identity, goal, rules, and tone.
Pick a voice and language
On the Advanced tab, choose the agent’s Text-to-Speech voice (use the preview button to listen before committing) and the Speech-to-Text language. OSVI supports English plus major Indian languages including Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Gujarati, Marathi, and Punjabi. Browse the full catalogue under Voices.
Test it in the playground
Use the test panel on the agent page to start a web call straight from your browser — no phone involved. You’ll see a live transcript as you talk. Switch the test mode to chat to try the same agent over text.Iterate here: tweak the prompt, test again, repeat. This loop is much faster than real phone calls.
Go live
When the agent behaves the way you want, pick a path:
Receive calls
Attach a phone number so the agent answers inbound calls.
Run a campaign
Upload a CSV of contacts and let the agent work through the list.
Trigger calls via API
POST /v1/call with a phone number and your agent’s UUID.Get results back
Set up post-call analysis and webhooks to receive summaries and extracted data.
