AI Model API

Audio

Entry point for speech synthesis and audio capability documentation

Overview

This section covers audio-related APIs such as speech synthesis. It currently provides commonly used entry points for the Gemini and Doubao model families.

Seed TTS 1.0

Doubao text-to-speech API from ByteDance.

Seed TTS 2.0

New-generation Doubao text-to-speech API from ByteDance.

Gemini 2.5 Flash Preview TTS

Entry point for lightweight Gemini speech synthesis.

Gemini 2.5 Pro Preview TTS

Entry point for high-quality Gemini speech synthesis.

How is this guide?

Last updated on

Proxy Video Content GET

doubao-seedance-2-0-fast-260128 Proxy Video Content API

Speech Generation POST

gemini-2.5-flash-preview-tts Speech Generation API