Gemini Live Avatar Demo

Access & Authentication

Project ID *

Location / Region *

Access Token (Optional)

Priority PayGo (lower latency, prioritized capacity for Agent Platform tools)

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 Google Search Grounding

Send Location

Send Current Date, Time & Timezone

Voice Activity Detection (VAD) & Turn-Taking

Silence Duration: 800 ms Wait time before model starts replying

Prefix Padding: 300 ms Audio buffer prepended to speech

Barge-in Sensitivity

End of Speech Sensitivity

Explicit Server VAD Signal (ACTIVITY_START / ACTIVITY_END)

Custom Vocabulary (Transcription Hints) Comma-separated domain terms, product names, or proper nouns (up to 1,000 terms)

Enable Context Window Compression

Trigger Tokens:

Greeting

Context

Tools

🖼️ Visual Display Surface (Image & SVG Tools) Stage: Auto

Offer open_modal(message) Tool

Behavior

Scheduling

Offer generate_image(prompt, resolution?) Tool

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($prompt supported). Leave empty to disable.

Offer show_svg, update_svg, review_and_improve_svg & highlight_canvas_element Tools

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($type, $title, and $prompt supported). Leave empty to disable.

Offer set_timer(duration) Tool

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($duration supported). Leave empty to disable.

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

System Instructions / Persona

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

ℹ️ System instructions can be edited during an active session. Click "Context Update" to apply changes.

System Context

Available variables: $name, $mood, $location, $dateTime, $timezone, $userGivenName, $userFamilyName, $otherAvatarName

ℹ️ System Context is injected into the conversation history as a user message (role: 'user') and will be compacted if Context Window Compression is enabled.

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 Google Search Grounding

Send Location

Send Current Date, Time & Timezone

Voice Activity Detection (VAD) & Turn-Taking

Silence Duration: 800 ms Wait time before model starts replying

Prefix Padding: 300 ms Audio buffer prepended to speech

Barge-in Sensitivity

End of Speech Sensitivity

Explicit Server VAD Signal (ACTIVITY_START / ACTIVITY_END)

Custom Vocabulary (Transcription Hints) Comma-separated domain terms, product names, or proper nouns (up to 1,000 terms)

Enable Context Window Compression

Trigger Tokens:

Greeting

Context

Tools

🖼️ Visual Display Surface (Image & SVG Tools) Stage: Auto

Offer open_modal(message) Tool

Behavior

Scheduling

Offer generate_image(prompt, resolution?) Tool

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($prompt supported). Leave empty to disable.

Offer show_svg, update_svg, review_and_improve_svg & highlight_canvas_element Tools

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($type, $title, and $prompt supported). Leave empty to disable.

Offer set_timer(duration) Tool

Behavior

Scheduling

Verbal Confirmation

Spoken immediately upon tool call ($duration supported). Leave empty to disable.

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

System Instructions / Persona

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

ℹ️ System instructions can be edited during an active session. Click "Context Update" to apply changes.

System Context

Available variables: $name, $mood, $location, $dateTime, $timezone, $userGivenName, $userFamilyName, $otherAvatarName

ℹ️ System Context is injected into the conversation history as a user message (role: 'user') and will be compacted if Context Window Compression is enabled.

Custom Avatar configuration

Hint: You can create a custom avatar by taking a photo, uploading an image (< 5 MB), or generating one from a prompt. For best Gemini 3.8 Live quality, use a front-facing head-and-shoulders bust shot (> 60% of frame) with closed lips, a neutral expression, no hands or held objects, and an uncluttered 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 official voice cloning 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 10–20 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 Target: 10–20s

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

Custom Voice Hash Copy or insert hash returned from WebSocket

Conversation History 0 turns

Auto-scroll

Context Window Compression is active: Older turns are compacted server-side by Agent Platform when token limits are reached. This client-side history caches all raw interaction turns, as sliding-window compression is handled within the server and cannot be read back.

No conversation messages recorded yet. Start a session or speak with the avatar to view turns.

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
Cached Content Tokens	0
Tool Use Prompt Tokens	0
Thoughts Tokens (Reasoning)	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
Cached Content Tokens	0
Tool Use Prompt Tokens	0
Thoughts Tokens (Reasoning)	0
Total Tokens	0

Advanced Settings

Custom Background

Background Prompt

Image URL

Stage Visual

Gemini Live Avatar Configuration

General

Avatar 1

Avatar 2

Feature Walkthrough

Keyboard Control Active

Customize Avatar Position & Size

Visual Effects

Troubleshoot Package Inspector