Gemini 3.1 Flash TTS
google / gemini-3-1-flash-tts

Gemini 3.1 Flash TTS 预览版是 Google 推出的一款富有表现力的文本转语音(TTS)模型。它能够生成自然逼真的 AI 语音,并可对语调、情感、语速和说话风格进行精准控制。

Pricing: Input 140 credits / 1M tokens (≈ $0.70), Audio Output 2,800 credits / 1M tokens (≈ $14.00). ~30% cheaper than official pricing. High-tier top-ups (+10% bonus) bring effective pricing down to ~90% of the above.
Input
0 / 2
No items yet. Click Add to start.

At least 1 item(s) required

0
No items yet. Click Add to start.

At least 1 item(s) required

Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused. Default value: 1

scene description

0/1000

Example Context / Overall Tone

0/1000
Output
output typeaudio

README

Complete guide to using google/gemini-3-1-flash-tts

Gemini 3.1 Flash TTS API:生成自然且富有表现力的语音

界面组件首屏演示图
Feature image
借助 Gemini 3.1 Flash TTS API 生成更自然的音频
通过 Gemini 3.1 Flash TTS API 的音频标记控制语音演绎
通过 Google Gemini 3.1 Flash TTS API 打造专属语音风格
使用 Gemini 3.1 Flash TTS 预览版 API 打造更丰富的对话体验
借助 Gemini 3.1 Flash 文本转语音 API 打造多语言体验
使用 gemini-3.1-flash-tts-preview API 构建灵活的语音应用
对比维度Gemini 3.1 Flash TTSGemini 2.5 Flash TTSEleven v3Inworld TTS
Model PositioningExpressive speech generation model designed for natural delivery, detailed control, and scalable multilingual audio creationEarlier Gemini TTS model focused on efficient and general speech synthesisAdvanced voice generation model focused on highly expressive and realistic speechCharacter-focused speech model designed for interactive AI experiences
Speech NaturalnessStrong naturalness with improved vocal clarity, conversational rhythm, and expressive variationProvides natural speech output with less refined delivery controlHigh-quality voice realism with strong emotional performanceNatural character-style voices optimized for interactive scenarios
Expressive ControlAudio tags and natural-language instructions provide detailed control over emotion, pacing, pauses, and vocal styleSupports general voice instructions with fewer fine-grained controlsProvides voice style and emotional control through prompting and voice designEmphasizes personality-driven voice customization
Voice DirectionSupports speaker identity, scene context, accent, tone, and performance guidanceProvides basic style guidance for speech generationAllows detailed voice and character directionDesigned around creating unique AI characters and personalities
Multilingual CapabilitySupports more than 70 languages with multilingual speech generationSupports multilingual output with broader limitations compared with newer generation capabilitiesSupports multilingual voice generation across different regionsProvides multilingual capabilities for conversational applications
Multi-Speaker DialogueSupports multiple speakers with separate voice characteristics and delivery stylesProvides more limited dialogue generation capabilitiesSupports multi-voice creation depending on workflowStrong focus on character interaction and dialogue scenarios
Speech CustomizationEnables both global style direction and moment-level delivery adjustmentsMainly focused on overall voice generation settingsStrong customization through voice design and style controlStrong customization for interactive characters
  • 01
  • 02
  • 03
  • 04
  • 05
  • 06
  • 借助 Gemini 3.1 Flash TTS API 打造富有表现力的有声读物与故事旁白
    基于 Gemini 3.1 Flash TTS API 构建的交互式语音助手
    使用 Gemini 3.1 Flash 预览版 TTS API 创作多语言内容
    基于 Gemini 3.1 Flash 预览版 TTS API 的无障碍与企业级音频解决方案

    Gemini 3.1 Flash TTS API 是一款文本转语音模型,旨在将书面内容转化为自然且富有表现力的音频。它支持通过风格指令和音频标记进行细致的语音控制,让开发者能够针对不同的语音生成场景调整语调、语速、情感和表达风格。

    是的。Gemini 3.1 Flash TTS 支持 70 多种语言的语音生成,帮助开发者为全球用户打造本地化的音频体验。结合灵活的声音风格引导与丰富的表现力控制功能,能够实现更自然的多语言语音合成。请查阅最新的 Kie.ai API 文档,获取当前支持的语言列表及可用的语音选项。

    借助音频标记,开发者可以在文本中添加富有表现力的指令,从而精准引导特定片段的语音输出。该功能可用于控制情感、停顿、耳语、笑声及语速变化等元素,使生成的音频更加生动自然,非常适合用于旁白、对话及交互式应用。

    是的。Gemini 3.1 Flash TTS 支持多角色对话生成,可为每个说话人设定不同的声音特征与表达风格。借助该功能,开发者可以打造出更自然的对话、角色互动、教学对话以及具有鲜明身份特征的剧情音频体验。请查阅最新的 Kie.ai API 文档,了解支持的多角色配置、可用选项及具体集成指南。

    Gemini 3.1 Flash TTS API 支持广泛的语音应用场景,包括有声读物、播客、语音助手、无障碍工具、教育平台、本地化内容以及自动化商业通信。凭借其丰富的语音表现力控制与多语言支持功能,它非常适合需要生成生动 AI 语音的项目。

    可以。开发者可通过 Kie.ai 调用 Gemini 3.1 Flash TTS API,将富有表现力的 AI 语音生成功能集成到应用中。Kie.ai 提供了便捷的模型接入方式,助您轻松构建语音驱动的工作流,免去管理独立集成的繁琐工作。

    Kie.ai 上最新的 Gemini 3.1 Flash TTS API 文档详细介绍了集成方法、支持选项、可用功能及使用要求。建议开发者仔细查阅该文档,以获取最新的模型特性和 API 详情。