GPT-Live limitations and FAQs

GPT-Live has a different set of supported features from Vapi’s other voice architectures. Use this page to check the requirements of your application before migrating.

These limits describe Vapi’s GPT-Live integration. A capability in OpenAI’s direct API isn’t necessarily exposed through Vapi.

Jump to: Calls and voices · Transfers · Squads · Live control · Testing · Recordings

Calls and voice

Feature	Support
Browser WebRTC, native Twilio, and Vapi SIP	Supported
Raw WebSocket	Supported with mono, signed 16-bit little-endian PCM at 24 kHz. Set the rate explicitly
Native Telnyx or Vonage	Unsupported
22 preset OpenAI voices	Supported. See voice previews
Custom or cloned voices, or other voice providers	Unsupported
Changing voice during a call	Unsupported. Save the assistant and start a new call
Model and voice fallbacks	Unsupported. GPT-Live also cannot be a fallback model
Reconnecting to an existing GPT-Live session	Unsupported. Start a new call and check the status of pending work

See Connect a call for working connection examples.

Transfers and keypad input

Function tools, API request tools, and endCall are supported. The other supported tool types, transferCall and dtmf, depend on the call connection:

Feature	Support
Blind transfer	Supported on native Twilio and Vapi SIP to configured phone or SIP destinations
Transfer on browser or raw WebSocket calls	Unsupported
Warm transfer or generated transfer summary	Unsupported
Transfer fallback plans or SIP `bye` verb	Unsupported
SIP transfer with extension dialing	Unsupported. Use a direct destination
Outgoing DTMF	Supported on SIP using RTP DTMF. Pass digits as a string, for example `"0011*#"`
Outgoing DTMF on Twilio, browser, or raw WebSocket calls	Unsupported
SIP INFO DTMF	Unsupported
Incoming keypad collection	Unsupported. Leave `keypadInputPlan.enabled` disabled

Other tool types are unsupported. Expose external lookups through a function or API request tool. Carrier acceptance of a transfer doesn’t establish that the destination answered.

Can I use an existing squad?

Squads and assistant handoffs are currently unsupported. GPT-Live’s speaker and reasoner work within one assistant. Delegation doesn’t switch the caller to another assistant.

Early testing suggests some use cases no longer need the same divisions between assistants. See Start with one assistant for how to rethink the architecture while keeping your business requirements.

Can I inject commentary or control speech during a call?

Customer-initiated commentary injection, live message injection, and live call-control commands are currently unsupported. Incoming text commands on the raw WebSocket connection are ignored.

Vapi uses OpenAI’s commentary mechanism internally to pass reasoner results to the speaker. That doesn’t expose session.commentary.append as a customer API. Use the supported tool response flow to return results for requested work.

A caller can ask the assistant to slow down or explain differently, and you can prompt it to respond to those requests. That conversational behavior is separate from an application sending a control command.

Can I guarantee exact speech or a fixed pause?

GPT-Live generates speech and may paraphrase supplied text. Speaker instructions and personality packs guide delivery. They don’t provide exact playback, a fixed speaking rate, or a programmatic pause while work completes.

Audio URL greetings and the generated-message first-message mode are unsupported. Use a text firstMessage with assistant-speaks-first, or let the assistant wait for the caller. Without usable greeting text, it waits.

If exact prerecorded wording or strict control of every spoken step is essential, choose an architecture with those controls. See voice design for the choices available through prompting.

Which existing settings no longer apply?

Classic transcriber selection, text-to-speech controls, and start/stop-speaking plans don’t configure the GPT-Live conversation. General model fields such as temperature and maxTokens don’t tune this integration.

Use the speaker prompt for conversation behavior and the reasoner settings for task reasoning. The reasoner currently supports only the OpenAI models listed in Model settings.

Does an interruption cancel a tool call?

No. Interrupting speech changes the conversation, not an action already submitted to your service. Your application needs to check whether that action is pending, completed, or cancellable.

If the caller corrects a date during a lookup, use the result that matches the updated request. For an example, see When callers change the request.

Can I run Simulations and Evals?

Voice Simulations are currently incompatible with GPT-Live. The simulation bridge uses 16 kHz audio and listen sockets. GPT-Live’s raw WebSocket connection requires 24 kHz and doesn’t provide listen sockets.

Run voice scenarios through a supported call connection. Evals can supplement testing of supported model decisions, but they don’t establish GPT-Live’s audio quality, timing, or interruption behavior.

Recordings and post-call data

GPT-Live supports shared post-call analysis, structured outputs, scorecards, Boards, and Monitoring. Availability depends on your configuration and retained call data:

Setting or feature	Behavior
Recording disabled in the assistant	No recording is created
Recording-consent plan configured	Recording is disabled because GPT-Live doesn’t collect that consent
Transcript-based analysis	Requires the relevant conversation data
Audio-based analysis	Requires an available recording
Monitoring with Zero Data Retention	Unsupported
Live listen or monitor sockets	Unsupported. Post-call Monitoring doesn’t provide a live audio connection

See Review and monitor calls for setup and result fields.

Troubleshooting

Use the symptom to find the setting or handler to check:

Symptom	Check	Fix
GPT-Live is unavailable	Organization feature access	Contact Vapi to enable access.
Voice unsupported	`voice.provider` and `voice.voiceId`	Use OpenAI and a supported voice ID.
Tool configuration unsupported	Tool type and resolved names	Use supported types and unique names. Inspect saved tools too.
Call fails on WebSocket startup	Audio format and sample rate	Set raw `pcm_s16le` at `24000` Hz explicitly.
WebSocket audio sounds distorted	Sample encoding, rate, and channels	Convert the source to mono, signed 16-bit little-endian PCM at 24 kHz.
Assistant never greets	First-message mode and usable text	Set `assistant-speaks-first` and a text `firstMessage`.
Assistant promises a lookup but no tool runs	Both prompts and attached tools	Add a concrete delegation rule and make the tool available to the reasoner.
Tool result never reaches the conversation	Handler response and matching ID	Return the actual `toolCallId`. Return the final async result through the original handler request.
Transfer fails	Transport and configured destination	Use a supported blind transfer. Check carrier requirements and destination restrictions.
No recording	Recording settings and consent plan	Check the documented recording behavior before the test.