Gemini Live Avatar Demo

Authentication

Project ID *

Location *

Access Token (Optional)

Avatar setup

Avatar Preset

Voice

Model

Language

Thinking Level

Save and download video session

Enable Transparency with Tolerance: 50

Show Transcript

Enable Chat Input

Enable Session Resumption

Enable Google Search Grounding

Send Location

Voice Activity Detection (VAD) & Turn-Taking

Silence Duration: 300 ms Wait time before model starts replying

Prefix Padding: 100 ms Audio buffer prepended to speech

Barge-in Sensitivity

End of Speech Sensitivity

Enable Context Window Compression

Trigger Tokens:

Greeting

Context

Tools

Offer open_modal(message) Tool

Behavior

Scheduling

Offer generate_image(prompt) Tool

Behavior

Scheduling

Offer set_timer(duration) Tool

Behavior

Scheduling

ℹ️ Disabled by default. When enabled, tools demonstrate async function calling and scheduling.

Header

⚠️ Avoid mid-session edits (impacts prefix caching & latency). Only use for rare, high-priority static information (e.g. storage approvals).

System Instructions / Persona

Available variables: $name (Avatar name), $mood (Mood), $voiceDescription (Voice style), $language (Language), $location (Coordinates), $userGivenName (User first name), $userFamilyName (User last name), $otherAvatarName (Other avatar name)

ℹ️ System instructions are non-editable during an active session. Any persona or prompt context that may need updating mid-session should go into the Footer.

Footer

ℹ️ Use for all dynamic information from the system prompt that can change mid-session.

Avatar 2 setup

Avatar Preset

Voice

Model

Language

Thinking Level

Save and download video session

Enable Transparency with Tolerance: 50

Show Transcript

Enable Chat Input

Enable Session Resumption

Enable Google Search Grounding

Send Location

Voice Activity Detection (VAD) & Turn-Taking

Silence Duration: 300 ms Wait time before model starts replying

Prefix Padding: 100 ms Audio buffer prepended to speech

Barge-in Sensitivity

End of Speech Sensitivity

Enable Context Window Compression

Trigger Tokens:

Greeting

Context

Tools

Offer open_modal(message) Tool

Behavior

Scheduling

Offer generate_image(prompt) Tool

Behavior

Scheduling

Offer set_timer(duration) Tool

Behavior

Scheduling

ℹ️ Disabled by default. When enabled, tools demonstrate async function calling and scheduling.

Header

⚠️ Avoid mid-session edits (impacts prefix caching & latency). Only use for rare, high-priority static information (e.g. storage approvals).

System Instructions / Persona

Available variables: $name (Avatar name), $mood (Mood), $voiceDescription (Voice style), $language (Language), $location (Coordinates), $userGivenName (User first name), $userFamilyName (User last name), $otherAvatarName (Other avatar name)

ℹ️ System instructions are non-editable during an active session. Any persona or prompt context that may need updating mid-session should go into the Footer.

Footer

ℹ️ Use for all dynamic information from the system prompt that can change mid-session.

Custom Avatar configuration

Hint: You can create a custom avatar by taking a photo, uploading an image, or generating one from a prompt. For best results with camera input, ensure a uniform background.

Select Avatar to Edit

Language for Defaults

Avatar Name *

Gender:

Default Voice:

Voice Description:

Mood:

Default Greeting:

Auto-Improve

Image Generation Prompt

Generation Format:

Create Custom Voice

⚠️

Sensitive Technology Consent Required Voice cloning is a highly sensitive technology. You MUST obtain explicit, documented consent from the person whose voice is being cloned before recording and using their voice sample.

Voice Name *

Select script to read during recording:

"When the sunlight strikes raindrops in the air, they act like a prism and form a rainbow. The rainbow is a division of white light into many beautiful colors. These take the shape of a long round arch."

🎙️ Tips for the best 15-second recording:

Speak naturally: Don't use your "radio voice" or over-enunciate. Read it exactly as you would speak to a friend.
Background noise: Limit background noise as much as possible. Turn off fans, AC units, and close windows.
Smile slightly!: Smile during the audio recording to add warmth to the replicated voice.

Step 1: Record Voice Sample

Not recorded

Step 2: Record Consent Statement

Speak this sentence exactly: "I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model."

Not recorded

Advanced Settings

Custom Background

Background Prompt

Image URL

Session Statistics

General

Downlink: - Mbps

RTT: - ms

CPU Pressure: -

Avatar 1

Initial latency:

Total: - ms

Latency:

Avg: - ms (Curr: - ms)

Session Duration: - s

Transparency: - ms (avg: - ms, -, -)

Video Playback: 0 dropped frames

Packet Jitter: - ms

Video Codec: Auto

Interruptions: 0

Message Metric	Sent	Received
Audio Messages	0	0
Video Messages	0	0
Text Messages	0	0
Total Messages	0	0

Token Metric	Tokens
Prompt Tokens (Input)	0
Model Tokens (Output)	0
Total Tokens	0

Avatar 2

Initial latency:

Total: - ms

Latency:

Avg: - ms (Curr: - ms)

Session Duration: - s

Transparency: - ms (avg: - ms, -, -)

Video Playback: 0 dropped frames

Packet Jitter: - ms

Video Codec: Auto

Interruptions: 0

Message Metric	Sent	Received
Audio Messages	0	0
Video Messages	0	0
Text Messages	0	0
Total Messages	0	0

Token Metric	Tokens
Prompt Tokens (Input)	0
Model Tokens (Output)	0
Total Tokens	0

Gemini Live Avatar Configuration

General

Avatar 1

Avatar 2

Feature Walkthrough

Keyboard Control Active

Customize Avatar Position & Size

Visual Effects

General

Avatar 1

Avatar 2

Feature Walkthrough

Take Photo

Token Verification Failed

Notification

Keyboard Control Active

Customize Avatar Position & Size

Visual Effects