diff --git a/fern/docs.yml b/fern/docs.yml index f41bc7aef..9a5fcdfe6 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -91,6 +91,7 @@ layout: page-width: full content-width: 55rem sidebar-width: 300px + show-nav-availability-badges: true analytics: posthog: api-key: ${POSTHOG_PROJECT_API_KEY} @@ -317,16 +318,22 @@ navigation: path: tools/custom-tools-troubleshooting.mdx icon: fa-light fa-wrench - section: GPT-Live + icon: fa-light fa-microphone-lines + availability: beta collapsed: true contents: - page: Overview path: gpt-live/overview.mdx + availability: stable - page: Design your assistant path: gpt-live/design.mdx + availability: stable - page: Configuration path: gpt-live/configuration.mdx + availability: stable - page: Limitations and FAQs path: gpt-live/limitations.mdx + availability: stable - page: Custom keywords path: customization/custom-keywords.mdx icon: fa-light fa-bullseye diff --git a/fern/gpt-live/configuration.mdx b/fern/gpt-live/configuration.mdx index 95f11b4b2..71e72f90e 100644 --- a/fern/gpt-live/configuration.mdx +++ b/fern/gpt-live/configuration.mdx @@ -337,13 +337,13 @@ Send this body to `POST https://api.vapi.ai/call` with your Vapi private API key Connect to `transport.websocketCallUrl` in the response. Send and receive binary audio frames containing signed 16-bit little-endian samples at 24 kHz. Convert your microphone audio to that format before sending it. -Set `24000` explicitly. The default WebSocket rate is too low for GPT-Live. Browser WebRTC and phone connections negotiate their own audio formats. +Set `sampleRate` to `24000` for GPT-Live. Browser WebRTC and phone connections negotiate their own audio formats. Close the WebSocket to end the call, or have the assistant invoke `endCall`. Incoming JSON call-control commands are not supported by this GPT-Live connection. See [WebSocket transport](/calls/websocket-transport) for the general transport, applying the restrictions above. ## Review and monitor calls -Completed GPT-Live calls use Vapi's shared post-call processing. Configure the features you need, then inspect the results after a test call finishes. +GPT-Live supports post-call analysis, structured outputs, scorecards, Boards, and Monitoring. Configure the features you need, then inspect the results after a test call finishes. | Feature | Setup and results | | --- | --- | diff --git a/fern/gpt-live/limitations.mdx b/fern/gpt-live/limitations.mdx index 7a20c68e0..c9b77f0fd 100644 --- a/fern/gpt-live/limitations.mdx +++ b/fern/gpt-live/limitations.mdx @@ -52,9 +52,7 @@ Early testing suggests some use cases no longer need the same divisions between ## 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](/gpt-live/configuration#connect-your-tools) to return results for requested work. +Commentary injection, live message injection, and live call-control commands are currently unsupported. The raw WebSocket connection supports audio streaming only. Use the supported [tool response flow](/gpt-live/configuration#connect-your-tools) 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. @@ -80,13 +78,13 @@ If the caller corrects a date during a lookup, use the result that matches the u ## 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. +Voice Simulations are currently unsupported for GPT-Live. Run voice scenarios through a [supported call connection](/gpt-live/configuration#connect-a-call). [Evals](/observability/evals-quickstart) 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: +GPT-Live supports post-call analysis, structured outputs, scorecards, Boards, and Monitoring. Availability depends on your configuration and retained call data: | Setting or feature | Behavior | | --- | --- | diff --git a/fern/gpt-live/overview.mdx b/fern/gpt-live/overview.mdx index b5a8b9131..143d368fe 100644 --- a/fern/gpt-live/overview.mdx +++ b/fern/gpt-live/overview.mdx @@ -10,9 +10,25 @@ GPT-Live is an OpenAI voice model that can listen and speak at the same time. A Vapi connects that conversation to your tools and phone numbers, and provides the call records, analysis, and monitoring around it. -GPT-Live must be enabled for your Vapi organization. If you don't have access yet, [join the waitlist](https://vapi.ai/gpt-live-waitlist). We're admitting users from the waitlist every day. +**Private beta.** GPT-Live must be enabled for your Vapi organization. If you don't have access yet, [join the waitlist](https://vapi.ai/gpt-live-waitlist). We're admitting users from the waitlist every day. +## In this guide + +Start here for an overview, then choose what you need next. + + + + Plan speaker and reasoner roles, conversation flow, and speaking style. + + + Create an assistant, choose a voice, connect tools, and make a call. + + + Check supported features and what to consider before migrating. + + + ## How it works A GPT-Live assistant uses a **speaker** for the spoken interaction and a **reasoner** for tasks that need tools or detailed procedures. **Delegation** is the speaker asking the reasoner to handle one of those tasks. @@ -50,10 +66,4 @@ You also have more to design than the words alone. Set a voice, give the speaker GPT-Live has a different set of supported features from Vapi's other voice architectures. Check [Limitations and FAQs](/gpt-live/limitations) if your application depends on squads, live call control, simulations, or a specific transfer flow. -## Get started - -- **Explore the experience:** read [Design your assistant](/gpt-live/design) for architecture, conversation flow, and voice design. -- **Build a working assistant:** follow [Configure GPT-Live](/gpt-live/configuration#create-an-assistant) in the dashboard or API. -- **Assess a migration:** review [Limitations and FAQs](/gpt-live/limitations) against your current requirements. - For the underlying model, see OpenAI's [GPT-Live documentation](https://developers.openai.com/api/docs/guides/live). This section describes Vapi's integration and its supported configuration.