You can now use ChatGPT to launch production-ready AI voice agents for real phone workflows.
→ Build an agent with the right prompt, tone, language, voice, and call behaviors
→ Deploy to a live phone number
→ Test scenarios with test calls or chats: booking, escalation, voicemail, and more
→ Monitor call performance and iterate over time
Launch your first agent in ChatGPT with the Retell GPT App
When a caller speaks slowly, the agent slows down. When they speak fast or start to respond more eagerly, it speeds up to match. If they ask the agent to change pace, it adjusts immediately.
→ Elderly and hearing-impaired callers get a patient, measured pace
→ Fast-paced callers get snappy responses that respect their time
→ Non-native speakers get an agent that mirrors their rhythm
→ Any caller can say "slow down" or "talk faster" and the agent responds naturally
One agent configuration now handles the pace of every caller, automatically.
Split call traffic by percentage across multiple agents
→ Test a new prompt on 20% of inbound support calls
→ Compare two voices on outbound sales calls
→ See which agent performs best in your call analytics before rolling it out to 100%
Works for inbound and outbound calls. Set agent weights, deploy, and iterate.
Read A/B Testing Docs
Copy, Paste, and Undo Shortcuts: Use Cmd/Ctrl+C, Cmd/Ctrl+V, to copy and paste nodes across CF agents and components, or and Cmd/Ctrl+Z quickly undo changes.
New Node-Level Overrides: Override agent defaults per conversation node with controls for voice speed, responsiveness, and even the LLM.
Node Functions for Conversation Nodes: Add tools/functions to a specific conversation node.
Global Node Cooldown: Prevent a global node from firing again immediately after it triggers by pausing it for a set number of node steps.
Webhook Event Controls: Choose exactly which events each webhook receives, including new transfer events like started, bridged, cancelled, and ended.
Timezone-Based Hour Variables: Use built-in dynamic variables like current_hour_[timezone] to reference the current hour in a specific timezone.
ElevenLabs v3 Voices: Retell now supports ElevenLabs v3 voices, bringing more expressive speech with stronger emotion, cadence, and delivery. A strong fit for teams optimizing for voice quality and realism.
Data Retention Periods: Set how long call and chat data is kept per agent, then have it automatically and permanently deleted when that window expires.
PCAP Downloads for Call Debugging: Download packet capture files from the call details page to troubleshoot network or audio issues with tools like Wireshark.
Deprecation of Phone Number Agent Fields:
On March 31st, Retell will deprecate the old single-agent phone number fields in favor of weighted agent lists for inbound, outbound, and SMS routing.
If you use phone number APIs today: replace fields like inbound_agent_id and outbound_agent_id with inbound_agents, outbound_agents, inbound_sms_agents, and outbound_sms_agents.
No immediate action is required: existing data is converted automatically, and the APIs stay backwards-compatible until 03/31/2026 for single-agent setups.
TTS pricing adjustment:
A reminder that ElevenLabs pricing updates on March 23. Under the new model, ElevenLabs TTS starts at $0.04/min, with pricing varying by model.
We also have powerful alternatives with the introduction of Retell Platform Voices and the existing Minimax, Fish Audio, Cartesia, and OpenAI all at $0.015/min.
You can compare them directly in the playground, see the previous pricing announcement here.