gemini-2.5-pro-preview-tts

ttsproprietary

Our premium engine for studio-quality speech synthesis, offering high-fidelity and sophisticated audio generation. Gemini 2.5 Pro TTS is best for long-form content, professional narrations, and complex creative workflows that require the highest level of vocal clarity and natural prosody.

Context
8K
Max output
16K
Input price
$1.25/1M tokens
Output price
$10/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Creator Google AI
Licenseproprietary
Statusactive
Typetts
Input modalitiesaudio, image, text
Output modalitiesspeech
Open weightNo
Parameters—
Architecture—
Max chars—
Sample rate—
Voices—
Languages—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Generate ContentPOST
Generate text from multimodal inputhttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:generateContent
Stream ContentPOST
Stream text generation responseshttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:streamGenerateContent

Pricing

Text tokensPer 1M tokens
InputCached inputOutput
Standard$1.25—$10
Priority$2.25—$18
Flex$0.625—$5

Family Comparison: gemini-2.5

ModelContextMax outPricing
gemini-2.5-computer-use-preview-10-2025128K64K—
gemini-live-2.5-flash-preview———
gemini-2.5-flash-lite1.0M66K$0.1$0.4
gemini-2.5-flash-image-preview——$0.3$2.5
gemini-2.5-flash-image66K33K$0.3$2.5
gemini-2.5-flash-lite-preview-09-20251.0M66K$0.3$2.5
gemini-2.5-flash-native-audio-preview-12-2025131K8K$0.3$2.5
gemini-2.5-flash-preview-05-20——$0.3$2.5
gemini-2.5-flash-preview-09-20251.0M66K$0.3$2.5
gemini-2.5-flash-preview-09-25——$0.3$2.5
gemini-2.5-flash-preview-tts8K16K$0.3$2.5
gemini-2.5-flash1.0M66K$0.3$2.5
gemini-2.5-pro-preview-03-25——$1.25$10
gemini-2.5-pro-preview-05-06——$1.25$10
gemini-2.5-pro-preview-06-05——$1.25$10
gemini-2.5-pro-preview-tts8K16K$1.25$10
gemini-2.5-pro1.0M66K$1.25$10

API

GET/v1/models/vertex/gemini-2.5-pro-preview-tts

gemini-2.5-pro-preview-tts

Our premium engine for studio-quality speech synthesis, offering high-fidelity and sophisticated audio generation. Gemini 2.5 Pro TTS is best for long-form content, professional narrations, and complex creative workflows that require the highest level of vocal clarity and natural prosody.

Changes · 8 entries
gemini-2.5-pro-preview-ttsupdatee3d7dedAug 31, 2026, 04:13 AM
descriptionThe Interactions API is now generally available. We recom...→Our premium engine for studio-quality speech synthesis, o...
gemini-2.5-pro-preview-ttsupdate88d97e5Jun 30, 2026, 04:49 AM
descriptionOur premium engine for studio-quality speech synthesis, o...→The Interactions API is now generally available. We recom...
gemini-2.5-pro-preview-ttsupdatefa2bbbbMar 24, 2026, 05:22 AM
modalitiesinput["text","image","video","audio"]→["text","image","audio"]
descriptiona Latina Français Indonesia Italiano Polski Português – B...→Our premium engine for studio-quality speech synthesis, o...
taglinea Latina Français Indonesia Italiano Polski Português – B...→Our premium engine for studio-quality speech synthesis, o...
gemini-2.5-pro-preview-ttsupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
gemini-2.5-pro-preview-ttsupdateb301ebeMar 23, 2026, 11:47 PM
descriptiona Latina Français Indonesia Italiano Polski Português – B...
licenseproprietary
taglinea Latina Français Indonesia Italiano Polski Português – B...
open_weightno
gemini-2.5-pro-preview-ttsupdate7a4f1f6Mar 22, 2026, 05:43 AM
modalitiesoutput["text","image"]→["text","image","audio"]
pricinginput$1.25output$10batch input$0.625batch output$5tiers[{"label":"Text tokens","unit":"Per 1M tokens","columns":...
gemini-2.5-pro-preview-ttsupdateb50649fMar 21, 2026, 11:58 PM
model_typetts
tools["function_calling"]
endpoints["generateContent","streamGenerateContent"]
gemini-2.5-pro-preview-ttscreate7f5c66fMar 21, 2026, 05:16 AM