Gemini 2.5 Flash Native Audio (12-2025)

gemini/gemini-2.5-flash-native-audio-preview-12-2025

December 2025 Live API snapshot of Gemini 2.5 Flash native audio for real-time voice dialogue, with improved function calling and instruction following. Superseded by Gemini 3.1 Flash Live and now Gemini 3.8 Live; shutdown is scheduled for November 17, 2026.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/audio/speech-to-speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini/gemini-2.5-flash-native-audio-preview-12-2025",
  "input_audio": {
    "data": "BASE64_AUDIO",
    "format": "pcm16",
    "sample_rate": 16000,
    "channels": 1
  },
  "output_audio": {
    "format": "pcm16",
    "sample_rate": 24000
  }
}'

Input Price: $2.55 / 1M tokens
Output Price: $10.20 / 1M tokens
Input: Audio
Output: Audio

Capabilities

Explore what Gemini 2.5 Flash Native Audio (12-2025) supports, then use the API section for a request tailored to this model.

BatchRealtimeDuplexAudio inputAudio outputToolsPreview

Languages

Multilingual

Model Information

Provider: Google Gemini
Product: Conversational
Release Date: Dec 12, 2025
Data Policy: Configurable
Region: Global
Input: Audio
Output: Audio

Provider Documentation

Playground

Try Gemini 2.5 Flash Native Audio (12-2025) by Google Gemini. Requests use the selected workspace’s credits and API pricing.

Gemini 2.5 Flash Native Audio (12-2025)

This model uses a dedicated input format. Explore its API example or open the supported playground.

Open playground

Providers

Compare available endpoints, pricing, and context limits for Gemini 2.5 Flash Native Audio (12-2025).

Provider	Context	Output	Input Price	Output Price	Endpoint
Google Gemini	Not specified	Audio	$2.55 / 1M tokens	$10.20 / 1M tokens	`gemini/gemini-2.5-flash-native-audio-preview-12-2025:gemini`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Input formats	pcm16
Input sample rate	16000
Output formats	pcm16
Output sample rate	24000
Max session seconds	900

Provider Notes

Gemini 3.1 Flash Live Preview and Gemini 2.5 Flash Native Audio Preview are Live API models, not Gemini TTS endpoints. Both support the AudioLab realtime WebSocket and one-turn REST wrapper with mono PCM16 at 16 kHz input and 24 kHz output. AudioLab translates portable function tools to Gemini functionDeclarations and portable function results to toolResponse messages. Output transcription is the portable way to receive text because native-audio sessions use AUDIO as their sole response modality. Gemini 3.1 does not support proactive audio or affective-dialog configuration; those experimental controls remain model-specific.

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/audio/speech-to-speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini/gemini-2.5-flash-native-audio-preview-12-2025",
  "input_audio": {
    "data": "BASE64_AUDIO",
    "format": "pcm16",
    "sample_rate": 16000,
    "channels": 1
  },
  "output_audio": {
    "format": "pcm16",
    "sample_rate": 24000
  }
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`gemini/gemini-2.5-flash-native-audio-preview-12-2025` — Required model identifier.
`api_version (v1beta or v1alpha)`	View Accepted Values
`generationConfig / thinkingConfig`	View Accepted Values
`realtimeInputConfig`	View Accepted Values
`sessionResumption / contextWindowCompression`	View Accepted Values
`proactivity`	View Accepted Values
`portable function tools`	View Accepted Values
`provider.event (native Live API messages)`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Input formats	pcm16
Input sample rate	16000
Output formats	pcm16
Output sample rate	24000
Max session seconds	900

Similar Models

Explore more conversational and compare their capabilities.

Model	Context	Input Price	Output Price
Gemini 3.5 Live TranslateGoogle Gemini	Not specified	$2.975 / 1M tokens	$17.85 / 1M tokens
Gemini 3.1 Flash Live PreviewGoogle Gemini	Not specified	$2.55 / 1M tokens	$10.20 / 1M tokens
Grok Voice LatestxAI	Not specified	$0.0425 / minute	—
GPT Realtime 2.1OpenAI	Not specified	$27.20 / 1M tokens	$54.40 / 1M tokens
GPT Realtime 2.1 MiniOpenAI	Not specified	$8.50 / 1M tokens	$17.00 / 1M tokens
GPT Realtime 2OpenAI	Not specified	$27.20 / 1M tokens	$54.40 / 1M tokens

View All Conversational