Skip to content

feat(voice-agents): vapi settings recommendations #327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 20, 2025
Merged

feat(voice-agents): vapi settings recommendations #327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
42d7f15
add vapi images
m-ods Jun 19, 2025
652dcbd
add vapi settings section
m-ods Jun 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added fern/assets/img/vapi/vapi-start-speaking-settings.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added fern/assets/img/vapi/vapi-stop-speaking-settings.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added fern/assets/img/vapi/vapi-transcriber-settings.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
46 changes: 39 additions & 7 deletions fern/pages/02-speech-to-text/universal-streaming/voice-agents/vapi.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,14 @@

Vapi is a developer platform for building voice AI agents, they handle the complex backend of voice agents for you so you can focus on creating great voice experiences. In this guide, we'll show you how to integrate AssemblyAI's streaming speech-to-text model into your Vapi voice agent.

<Card
title="Vapi"
icon={<img src="https://assemblyaiassets.com/images/Vapi.svg" alt="Vapi logo"/>}
href="https://docs.vapi.ai/providers/transcriber/assembly-ai"
<Card
title="Vapi"
icon={
<img src="https://assemblyaiassets.com/images/Vapi.svg" alt="Vapi logo" />
}
href="https://docs.vapi.ai/providers/transcriber/assembly-ai"
>
View Vapi's AssemblyAI STT provider documentation.
View Vapi's AssemblyAI STT provider documentation.
</Card>

## Quick start
Expand All @@ -26,7 +28,7 @@

**Click on your assistant and then the "Transcriber" tab.**

<Frame>
<Frame>
<img src="/assets/img/vapi/Vapi-Step2.png" />
</Frame>

Expand All @@ -35,12 +37,42 @@
<Frame>
<img src="/assets/img/vapi/Vapi-Step3.png" />
</Frame>

</Steps>

Your voice agent now uses **AssemblyAI** for speech-to-text (STT) processing.

<Info>
New to Vapi? Visit the [Quickstart Guide](https://docs.vapi.ai/quickstart/introduction) to explore various example voice agent workflows. For the easiest way to test a voice agent, follow this [simple phone-based guide](https://docs.vapi.ai/quickstart/phone). Vapi offers a wide range of example workflows to get you up and running quickly.
New to Vapi? Visit the [Quickstart
Guide](https://docs.vapi.ai/quickstart/introduction) to explore various
example voice agent workflows. For the easiest way to test a voice agent,
follow this [simple phone-based guide](https://docs.vapi.ai/quickstart/phone).
Vapi offers a wide range of example workflows to get you up and running
quickly.
</Info>

## Recommended settings for optimal latency

### Transcriber settings

For best latency, Format Turns should be turned off (adds about 50ms of delay), and Universal Streaming should be enabled.

<Frame>
<img src="/assets/img/vapi/vapi-transcriber-settings.png" />
</Frame>

### Advanced > Start speaking plan

Check warning on line 64 in fern/pages/02-speech-to-text/universal-streaming/voice-agents/vapi.mdx

View workflow job for this annotation

GitHub Actions / lint 

[vale] reported by reviewdog 🐶
[AssemblyAI.Headings] Use sentence-style capitalization for 'Advanced > Start speaking plan'. 

Raw Output:
{"message": "[AssemblyAI.Headings] Use sentence-style capitalization for 'Advanced \u003e Start speaking plan'. ", "location": {"path": "fern/pages/02-speech-to-text/universal-streaming/voice-agents/vapi.mdx", "range": {"start": {"line": 64, "column": 5}}}, "severity": "WARNING"}

For start speaking plan, raise the `Wait seconds` to prevent false starts. `Smart Endpointing` should be turned off.

<Frame>
<img src="/assets/img/vapi/vapi-start-speaking-settings.png" />
</Frame>

### Advanced > Stop speaking plan

Check warning on line 72 in fern/pages/02-speech-to-text/universal-streaming/voice-agents/vapi.mdx

View workflow job for this annotation

GitHub Actions / lint 

[vale] reported by reviewdog 🐶
[AssemblyAI.Headings] Use sentence-style capitalization for 'Advanced > Stop speaking plan'. 

Raw Output:
{"message": "[AssemblyAI.Headings] Use sentence-style capitalization for 'Advanced \u003e Stop speaking plan'. ", "location": {"path": "fern/pages/02-speech-to-text/universal-streaming/voice-agents/vapi.mdx", "range": {"start": {"line": 72, "column": 5}}}, "severity": "WARNING"}

For stop speaking plan, lower `Voice seconds` to allow for faster interruptions.

<Frame>
<img src="/assets/img/vapi/vapi-stop-speaking-settings.png" />
</Frame>
Loading