GPT-Live limitations and FAQs

The content of this page has moved. Supported features are in Settings and compatibility, and the answers to these questions are in the guides linked below.

Calls and voice

See Calls and voice in Settings and compatibility.

Transfers and keypad input

See Transfers and keypad input in Settings and compatibility, and Transfer to a person.

Can I use an existing squad?

Squads and handoffs aren’t supported with GPT-Live. See Migrate to GPT-Live: From a squad.

Can I inject commentary or control speech during a call?

See Live call control.

Can I use idle-message hooks?

Yes. See When the caller goes quiet for an example and Idle messages for the settings.

Can I guarantee exact speech or a fixed pause?

No. GPT-Live generates all of its speech. See Speaking style.

Does the reasoner get the conversation transcript?

See What context does the reasoner receive?

Which existing settings no longer apply?

See Settings that no longer apply and the settings map for migration.

Does an interruption cancel a tool call?

No. See When callers change the request.

Can I run Simulations and Evals?

See Repeat scenarios with Voice Simulations.

Recordings and post-call data

See Recordings and post-call data.

Troubleshooting

See Troubleshooting in Test and improve.