跳到正文
Vercel Blog(vercel.com)· Zachary Chen·· 2026-09-23品質評分66

Gemini 3.8 TTS模型現已在AI Gateway上線

Gemini 3.8 text-to-speech models now available on AI Gateway

重點導讀

Gemini 3.8 Flash‑Lite TTS 與 Gemini 3.8 Flash TTS 現已在 AI Gateway 上線,支援 100 多種語言的文本轉語音,支援長篇朗讀、交付控制和雙人對話。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

正文 · 原文

Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS from Google are now available on AI Gateway.

Both models generate speech from text in more than 100 languages and support long-form narration, control over delivery, and two-speaker dialogue.

  • google/gemini-3.8-flash-lite-tts is optimized for high-volume speech generation, with controls for tone, pacing, and line-by-line delivery.

  • google/gemini-3.8-flash-tts is optimized for expressive voice generation and custom character design, with controls for acting cues, pacing, accents, and conversational reactions.

To generate speech, pass either model ID to the AI SDK (7 or later):

import { generateSpeech } from 'ai';

import { gateway } from '@ai-sdk/gateway';

import { writeFile } from 'node:fs/promises';

const result = await generateSpeech({

model: gateway.speechModel('google/gemini-3.8-flash-lite-tts'),

text: 'Welcome to the audio edition.',

voice: 'Kore',

instructions: 'Warm, relaxed, and speaking slowly',

outputFormat: 'wav',

});

await writeFile('speech.wav', result.audio.uint8Array);

Generate a WAV file with Gemini 3.8 Flash-Lite TTS.

Try Flash-Lite TTS or Flash TTS in the model playground. See the text-to-speech guide for setup instructions, two-speaker dialogue, and more examples.

來源: Vercel Blog (vercel.com)
開啟原文

讀者討論

理性交流 · 即時討論