Voice agents API
Build real-time voice agents that listen, think, and speak. Wire up tools, knowledge, and phone numbers — and let agents hold the conversation.
curl -X POST https://api.speechify.ai/v1/agents \
-H "Authorization: Bearer $SPEECHIFY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Support Bot",
"prompt": "You are a friendly support agent for a SaaS product. Greet callers, answer questions about billing and account settings, and transfer to a human if you cannot help.",
"first_message": "Hi, this is Sabrina with support. How can I help today?",
"voice_id": "sabrina",
"language": "en",
"temperature": 0.7
}'Everything an agent needs
Tools & function calling
Let agents call your APIs mid-conversation to look things up, take actions, and complete tasks in real time.
Knowledge base
Ground every answer in your own content with built-in retrieval. Upload documents, files, and sitemaps.
Memory
Agents remember context within a conversation — and across calls — for interactions that feel continuous.
Phone numbers & telephony
Inbound and outbound calling over SIP. Provision numbers and connect agents straight to the phone network.
Webhooks & events
Stream conversation events to your backend as they happen, with signed, verifiable payloads.
Testing & simulation
Validate behavior before you ship with reply, tool, and full-conversation simulation tests.
By industry
Tuned to the workflows that matter most in your industry.
How we compare
Honest, side-by-side comparisons with the other voice-agent platforms.
One rate. Everything included.
Most platforms quote a platform fee, then bill the LLM, speech, and telephony on top. Speechify is one all-in rate per minute.
Five line items, each metered separately. The bill takes a spreadsheet.
- LLM
- Speech-to-text
- Text-to-speech
- Telephony orchestration
One line item. No passthrough, no token math — and 60 free minutes every month.
Read the full Voice Agents documentation
Guides for tools, knowledge bases, memory, phone numbers, webhooks, and testing.