Skip to content

Google · Speech

Gemini 2.5 Pro TTS

Google 🇺🇸SpeechGemini familyOne of its sources says the weights aren't publicly available.
From Empiriolabs's listing:
High-quality TTS preview for podcasts, audiobooks, and customer support, with expressive multi-speaker voices across 23+ languages.
llminfo IQ
≈ 115
Market median price
$102.17 /1M chars
Max context
8K
Listings
8

Evidence and sources

llminfo IQ ≈ 115, ranked among text to speech models. From 16 benchmarks. Little data behind it, so treat it as a rough estimate.How llminfo IQ is computedReleased 20 May 2025Maker HQ: US (according to Google's own website)
All rankings: #556 on OpenRouter today #618 on OpenRouter this week #686 on OpenRouter this monthSources: EmpirioLabs data, Models.dev data, llminfo researchPrimary data from EmpirioLabs from Models.dev: weights availability from llminfo research: release date

Input & output

as stated by the model's providers
Text
Text
Audio

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingPrompt cachingAudio inputBatch API

Listings

 Googlemodels/gemini-2.5-pro-preview-ttsSources: Google Generative AI API data docs, LiteLLM data, Models.dev data8K$1.00cache read $0.125batch $0.50$20.00batch $10.00$0.70$20.00—
 LlmgatewayInference by Googlegemini-2.5-pro-preview-ttsSource: LLMGateway dataNot published by the provider$1.00$20.00———
 Llmgatewaygemini-2.5-pro-preview-ttsSource: LLMGateway data8K$1.00$20.00———
 Meganovagemini/gemini-2.5-pro-ttsSource: MegaNova dataNot published by the provider$0.80$16.00———
 NanoGPTgemini-2.5-pro-preview-ttsSource: NanoGPTNot published by the provider————$102.17
 Empiriolabsgemini-2-5-pro-ttsSource: EmpirioLabs dataNot published by the provider$3.00$60.00———

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Speech

EmergentTTS-Eval14 related benchmarks · 14 results
Source: EmergentTTS-Eval data
Benchmarkvoice: Zephyr, strong-prompt
WER
Complex Pronunciation WER
Complex Pronunciation Win-Rate
Emotions WER
Show 10 more benchmarksHide 10 benchmarks
Benchmarkvoice: Zephyr, strong-prompt
Emotions Win-Rate
Foreign Words WER
Foreign Words Win-Rate
Paralinguistics WER
Paralinguistics Win-Rate
Questions WER
Questions Win-Rate
Syntactic Complexity WER
Syntactic Complexity Win-Rate
Win-Rate

Human preference

Data credits: EmergentTTS-Eval (Boson AI), Apache-2.0 (licence)

Around the web

Also known as: gemini-2-5-pro-tts, gemini-2.5-pro-preview-tts, gemini/gemini-2.5-pro-preview-tts, gemini/gemini-2.5-pro-tts, vertex_ai/gemini-2.5-pro-tts

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works