Skip to content

Commit 786d1a2

Browse files
dev-seth-vapidvsth
andauthored
docs: clarify GPT-Live guides and add section navigation (#1226)
* docs: remove GPT-Live implementation details from public guides * docs: add GPT-Live section navigation and beta badge --------- Co-authored-by: dev-seth-vapi <dev@devseth.com>
1 parent 26c192d commit 786d1a2

4 files changed

Lines changed: 29 additions & 14 deletions

File tree

‎fern/docs.yml‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -91,6 +91,7 @@ layout:
9191
page-width: full
9292
content-width: 55rem
9393
sidebar-width: 300px
94+
show-nav-availability-badges: true
9495
analytics:
9596
posthog:
9697
api-key: ${POSTHOG_PROJECT_API_KEY}
@@ -317,16 +318,22 @@ navigation:
317318
path: tools/custom-tools-troubleshooting.mdx
318319
icon: fa-light fa-wrench
319320
- section: GPT-Live
321+
icon: fa-light fa-microphone-lines
322+
availability: beta
320323
collapsed: true
321324
contents:
322325
- page: Overview
323326
path: gpt-live/overview.mdx
327+
availability: stable
324328
- page: Design your assistant
325329
path: gpt-live/design.mdx
330+
availability: stable
326331
- page: Configuration
327332
path: gpt-live/configuration.mdx
333+
availability: stable
328334
- page: Limitations and FAQs
329335
path: gpt-live/limitations.mdx
336+
availability: stable
330337
- page: Custom keywords
331338
path: customization/custom-keywords.mdx
332339
icon: fa-light fa-bullseye

‎fern/gpt-live/configuration.mdx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -337,13 +337,13 @@ Send this body to `POST https://api.vapi.ai/call` with your Vapi private API key
337337

338338
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.
339339

340-
Set `24000` explicitly. The default WebSocket rate is too low for GPT-Live. Browser WebRTC and phone connections negotiate their own audio formats.
340+
Set `sampleRate` to `24000` for GPT-Live. Browser WebRTC and phone connections negotiate their own audio formats.
341341

342342
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.
343343

344344
## Review and monitor calls
345345

346-
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.
346+
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.
347347

348348
| Feature | Setup and results |
349349
| --- | --- |

‎fern/gpt-live/limitations.mdx‎

Lines changed: 3 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -52,9 +52,7 @@ Early testing suggests some use cases no longer need the same divisions between
5252

5353
## Can I inject commentary or control speech during a call?
5454

55-
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.
56-
57-
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.
55+
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.
5856

5957
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.
6058

@@ -80,13 +78,13 @@ If the caller corrects a date during a lookup, use the result that matches the u
8078

8179
## Can I run Simulations and Evals?
8280

83-
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.
81+
Voice Simulations are currently unsupported for GPT-Live.
8482

8583
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.
8684

8785
## Recordings and post-call data
8886

89-
GPT-Live supports shared post-call analysis, structured outputs, scorecards, Boards, and Monitoring. Availability depends on your configuration and retained call data:
87+
GPT-Live supports post-call analysis, structured outputs, scorecards, Boards, and Monitoring. Availability depends on your configuration and retained call data:
9088

9189
| Setting or feature | Behavior |
9290
| --- | --- |

‎fern/gpt-live/overview.mdx‎

Lines changed: 17 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,25 @@ GPT-Live is an OpenAI voice model that can listen and speak at the same time. A
1010
Vapi connects that conversation to your tools and phone numbers, and provides the call records, analysis, and monitoring around it.
1111

1212
<Note>
13-
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.
13+
**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.
1414
</Note>
1515

16+
## In this guide
17+
18+
Start here for an overview, then choose what you need next.
19+
20+
<CardGroup cols={3}>
21+
<Card title="Design your assistant" icon="fa-light fa-comments" href="/gpt-live/design">
22+
Plan speaker and reasoner roles, conversation flow, and speaking style.
23+
</Card>
24+
<Card title="Configuration" icon="fa-light fa-sliders" href="/gpt-live/configuration">
25+
Create an assistant, choose a voice, connect tools, and make a call.
26+
</Card>
27+
<Card title="Limitations and FAQs" icon="fa-light fa-circle-question" href="/gpt-live/limitations">
28+
Check supported features and what to consider before migrating.
29+
</Card>
30+
</CardGroup>
31+
1632
## How it works
1733

1834
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
5066

5167
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.
5268

53-
## Get started
54-
55-
- **Explore the experience:** read [Design your assistant](/gpt-live/design) for architecture, conversation flow, and voice design.
56-
- **Build a working assistant:** follow [Configure GPT-Live](/gpt-live/configuration#create-an-assistant) in the dashboard or API.
57-
- **Assess a migration:** review [Limitations and FAQs](/gpt-live/limitations) against your current requirements.
58-
5969
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.

0 commit comments

Comments
 (0)