Skip to content

Google · Speech

Gemini 2.5 Flash TTS

Google 🇺🇸SpeechGemini familyOne of its sources says the weights aren't publicly available.

Newer version: Gemini 3.8 Flash TTS. Our catalogue has no release date for Gemini 2.5 Flash TTS. We compared the version names in our catalogue.

From Empiriolabs's listing:
Low-latency text-to-speech with single- and multi-speaker voices and controllable style, accent, and expressive tone for production apps.
Market median price
$51.17 /1M chars
Max context
8K
Listings
8
Providers
7

Evidence and sources

All rankings: #523 on OpenRouter today #597 on OpenRouter this week #668 on OpenRouter this monthSources: EmpirioLabs data, Models.dev dataPrimary data from EmpirioLabs from Models.dev: weights availability

Advantages and trade-offs

Compared with 10 representative speech models
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 market median prices.

Input & output

as stated by the model's providers
Text
Text
Audio

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingAudio inputBatch API

Listings

 Googlemodels/gemini-2.5-flash-preview-ttsSources: Google Generative AI API data docs, LiteLLM data, Models.dev data8K$0.50batch $0.25$10.00batch $5.00$10.00—
 LlmgatewayInference by Googlegemini-2.5-flash-preview-ttsSource: LLMGateway dataNot published by the provider$0.50$10.00——
 Llmgatewaygemini-2.5-flash-preview-ttsSource: LLMGateway data8K$0.50$10.00——
 Meganovagemini/gemini-2.5-flash-ttsSource: MegaNova dataNot published by the provider$0.40$8.00——
 NanoGPTgemini-2.5-flash-preview-ttsSource: NanoGPTNot published by the provider———$51.17
 Empiriolabsgemini-2-5-flash-ttsSource: EmpirioLabs dataNot published by the provider$1.50$30.00——

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 · 28 results
Source: EmergentTTS-Eval data
Benchmarkvoice: Zephyrvoice: Zephyr, strong-prompt
WER
Complex Pronunciation WER
Complex Pronunciation Win-Rate
Emotions WER
Show 10 more benchmarksHide 10 benchmarks
Benchmarkvoice: Zephyrvoice: 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

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

Around the web

  • Gemini 2.5 Pro  |  Gemini API  |  Google AI for Developers
    Skip to main content The Interactions API is now generally available. We recommend using this …Skip to main content The Interactions API is now generally available. We recommend using this API for access to all the latest features and models. Home Gemini API Docs Send feedback Gemini 2.5 Pro O…

    ai.google.dev

  • We're expanding our Gemini 2.5 family of models
    See more details about our 2.5 family of models in the latest Gemini technical report …See more details about our 2.5 family of models in the latest Gemini technical report . Gemini 2.5 Flash-Lite benchmarks table The preview of Gemini 2.5 Flash-Lite is now available in Google AI Studi…

    blog.google

  • Gemini 2.5 Pro update: Coding, web apps with Gemini
    It also continues to build on its strong foundation in native multimodality and long context; …It also continues to build on its strong foundation in native multimodality and long context; it has state-of-the-art performance in video understanding, with a score of 84.8% on the VideoMME benchma…

    blog.google

  • Google Gemini 2.5 Pro
    Pro The Google Gemini 2.5 Pro ( google.gemini-2.5-pro ) is a reasoning, multimodal model that …Pro The Google Gemini 2.5 Pro ( google.gemini-2.5-pro ) is a reasoning, multimodal model that excels at solving complex problems and is the most advanced reasoning Gemini model to date. This model is…

    docs.oracle.com

  • Gemini 2.5 Flash and Pro, Live API, and Veo 2 in the Gemini API - Google Developers Blog
    Google for Developers Community/Events Learn Blog YouTube Search Google for Developers Community/Events Learn Blog YouTube …Google for Developers Community/Events Learn Blog YouTube Search Google for Developers Community/Events Learn Blog YouTube Gemini Gemini 2.5 Flash and Pro, Live API, and Veo 2 in the Gemini API APRIL…

    developers.googleblog.com

  • Gemini 2.5 Flash-Lite  |  Gemini API  |  Google AI for Developers
    Skip to main content ai.google.dev uses cookies from Google to deliver and enhance the quality …Skip to main content ai.google.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more OK, got it On this page gemini-2.5-flash-lite The Int…

    ai.google.dev

  • Gemini 2.5 Flash-Lite Preview  |  Gemini API  |  Google AI for Developers
    Skip to main content The Interactions API is now generally available. We recommend using this …Skip to main content The Interactions API is now generally available. We recommend using this API for access to all the latest features and models. Home Gemini API Docs Send feedback Gemini 2.5 Flash…

    ai.google.dev

  • Google Gemini 2.5 Flash-Lite - docs.oracle.com
    Oracle Cloud Infrastructure Documentation All Pages Skip to main content Google Gemini 2.5 Flash-Lite The …Oracle Cloud Infrastructure Documentation All Pages Skip to main content Google Gemini 2.5 Flash-Lite The Google Gemini 2.5 Flash Lite model ( google.gemini-2.5-flash-lite ) is the fastest and most b…

    docs.oracle.com

  • Google rolling out Gemini 2.5 Flash to devs and Gemini app
    are able to “set thinking budgets to control cost vs quality.” Key specifications for Gemini …are able to “set thinking budgets to control cost vs quality.” Key specifications for Gemini 2.5 Flash in preview (gemini-2.5-flash-preview-04-17): Advertisement - scroll for more content Avatar for …

    9to5google.com

  • Gemini 2.5 Flash Text-to-Speech  |  Gemini API  |  Google AI for Developers
    On this page Documentation gemini-2.5-flash-preview-tts Our fastest engine for high-fidelity speech synthesis, offering low-latency and …On this page Documentation gemini-2.5-flash-preview-tts Our fastest engine for high-fidelity speech synthesis, offering low-latency and cost-efficient audio generation. Gemini 2.5 Flash TTS is best f…

    ai.google.dev

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