Try Kling Image V4 Long for Page Mockups from Kling AI →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryDiscoverModels and effects built by WiroBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick connectors and skills, choose a plan, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building
Explore models/
Audio & SpeechActive

Google Gemini 3.8 Live Voice Model

bygoogle

Google Gemini 3.8 Live is a low-latency audio model for voice agents. It streams natural 24 kHz speech, supports tool calling, and optional Search grounding.

Speech to SpeechRealtime ConversationVoice Agent
Model ID
gemini 3.8 live
Provider
google
Updated
Nov 7, 2026, 04:19
gemini 3.8 live
0
Comments
Average rating : 5 (1 users)
Providergoogle
Modelgemini 3.8 live
Speech to SpeechRealtime ConversationVoice Agent
wiro playground—google/gemini 3.8 live

Required. The voice of the AI assistant. It speaks the language of the conversation automatically.

Required. Instructions that define the AI assistant's behavior and personality.

Optional. None uses gemini-3.8-live for the fastest replies. Low, medium and high switch to gemini-3.8-live-extended-thinking, which reasons in the background and may say a short filler while it thinks (higher latency and cost).

Optional. Lets the assistant search Google for current information. Each search query is billed separately.

Audio $3/$12 per 1M input/output tokens. Text $0.75/$4.50 per 1M input/output tokens (thinking billed as text output). Image/video input $1/1M. Speech transcription included. Each spoken reply bills the full conversation context; with a thinking level above Standard, short fillers spoken while it thinks are billed as replies too. Google Search grounding $14 per 1,000 queries when web search is on.

Sample outputs

No samples yet

Run this model to create outputs and build up samples.

Updated Nov 7, 2026, 04:19

Overview

Gemini 3.8 Live is Google’s real-time, audio-first dialogue model for natural voice conversations. It listens to live 16 kHz PCM microphone audio and streams back 24 kHz PCM speech while the session stays open. It can also accept text, images, and video as context, then answer in audio and text. This model helps you build assistants that feel like a phone call, not a chat box.

What you can build

  • A customer support voice agent that answers, clarifies, and confirms details out loud
  • A hands-free assistant for field technicians who talk while working
  • A tutoring companion that explains steps in spoken form and handles follow-up questions
  • A voice concierge that can browse current facts with Search grounding when enabled
  • A multimodal voice helper that reacts to a camera feed or screenshots while speaking

Inputs

  • A required voice selection for the assistant’s speech, chosen from a fixed set of prebuilt voices. The model automatically speaks the conversation language.
  • Required system instructions (plain text) that define tone, style, and boundaries for the assistant.
  • An optional thinking depth setting. When you choose a non-none level, the run switches to the Extended Thinking variant for more background reasoning during live dialogue.
  • An optional toggle to allow Google Search grounding for current information.
  • Live microphone audio as raw 16-bit PCM (little-endian). A 16 kHz sample rate is the native and recommended format, with optional 8 kHz or 24 kHz input.
  • Optional speech start sensitivity that controls how easily the system treats sound as the start of speech.
  • Optional speech end sensitivity that controls how quickly the system ends your turn after you pause.
  • Optional silence duration (milliseconds) that sets how long you must be quiet before the assistant starts speaking.

Outputs

  • Streamed spoken responses as raw 16-bit PCM audio (little-endian) at 24 kHz.
  • Optional text transcripts of what you said, if input transcription is enabled by the platform.
  • Optional text alongside speech, such as short summaries or confirmations, depending on the experience design.

Recommended settings

  • Use 16 kHz, 16-bit PCM microphone input for best compatibility with the model’s native audio path.
  • Keep thinking set to none for the lowest-latency back-and-forth.
  • Switch thinking to low, medium, or high when you need multi-step reasoning during a live call.
  • Use high speech end sensitivity when you want faster turn-taking.
  • Lower speech start sensitivity in noisy rooms to reduce false triggers.

Limitations

  • Knowledge cutoff: January 2025. Use Search grounding if you need current facts.
  • Input limit is about 128K tokens and output limit is about 64K tokens, across supported modalities.
  • Structured outputs aren’t supported, so you can’t rely on strict JSON-only responses.
  • Context caching isn’t supported.
  • Code execution and file search aren’t supported.
  • Audio quality matters. Background noise, overlapping speech, and clipped microphones can reduce accuracy and timing.
  • Non-structured visual inputs can fail. Blurry photos, tiny text, or shaky video can cause wrong conclusions.

Safety & compliance

  • Follow Google’s Generative AI policies and the Gemini API terms for prohibited content and misuse.
  • Don’t use the model to generate or facilitate harmful, illegal, or privacy-invasive content.
  • Treat live audio as sensitive data. Get consent before recording, storing, or sharing user speech.
  • Validate important claims. Like other foundation models, it can hallucinate or misunderstand context.

API quick start

Run gemini 3.8 live with a single API call.

POST https://api.wiro.ai/v1/Run/google/gemini-3-8-live
{
  "voice": "Puck",
  "system_instructions": "You are a helpful voice assistant. Speak …",
  "thinking_level": "none",
  "web_search": "false"
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/google/gemini-3-8-live" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "voice": "Puck",
  "system_instructions": "You are a helpful voice assistant. Speak …",
  "thinking_level": "none",
  "web_search": "false"
}
JSON

Other models you might like

Explore similar audio & speech models.

View all
gpt-realtime-translate
Speech to Speech

gpt-realtime-translate

openai

gpt-live-1
Speech to Speech

gpt-live-1

openai

gpt-realtime-mini
Speech to Speech

gpt-realtime-mini

openai

gpt-realtime-2.1-mini
Speech to Speech

gpt-realtime-2.1-mini

openai

  • gpt-realtime-2.1openai
  • gpt-realtimeopenai
  • Realtime Conversational AIelevenlabs
  • PersonaPlex-Realtimenvidia
  • dubbingelevenlabs
  • noise-reductionlibrosa
  • voice clone v4elevenlabs
  • audio isolationelevenlabs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroModelsAgentsMCP ServerLLM GatewayBrowser ExtensionIntegrationsPricingAboutBlogCareersContactPartnerChangelogStatusFAQ
CategoriesText to ImageImage to ImageImage EditingImage to TextText to VideoImage to VideoVideo to VideoText to SpeechSpeech to TextSpeech to SpeechVoice CloneRealtime ConversationMusic GenerationLLMUtilities
ModelsNano Banana 2GPT Image 2.5Seedream V5 ProSeedance 2.5Veo 3.1Kling V3FLUX 3FLUX.2 ProWan 3.0 PrimeGrok Imagine 1.5
PartnersGoogleOpenAIByteDanceBlack Forest LabsKling AIQwenAlibabaxAIMiniMaxElevenLabs
Getting StartedWiro ModelsWiro EffectsIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion