MODELS

Fish Audio S2 Pro

by Fish Audio

modelsource:fish.audiotext-to-speechspeech-synthesisvoice-aiopen-source

Overview

Expressive text-to-speech model with natural-language emotion and prosody control, available through Fish Audio app/API and an open-source release.

Details

Fish Audio S2 Pro is an expressive text-to-speech model from Fish Audio. The supplied Fish Audio sources describe it as supporting natural-language control over emotion and prosody, and as being available through the Fish Audio app/API as well as an open-source release. Official discovery sources include the Fish Audio launch/blog page, Fish Audio documentation and quickstart pages, and the fishaudio/fish-speech GitHub repository.

When to Use

Use when you need a text-to-speech model with natural-language emotion and prosody control. Use when evaluating Fish Audio’s app/API offering alongside its open-source Fish Speech repository. Use when building or comparing catalog entries for expressive speech synthesis models.

Getting Started

Read the Fish Audio S2 Pro launch/open-source announcement: https://fish.audio/blog/fish-audio-open-sources-s2/
Review the Fish Audio documentation: https://docs.fish.audio/
Follow the Fish Audio quickstart page for initial setup guidance: https://docs.fish.audio/docs/getting-started/quickstart
Inspect the official GitHub repository: https://github.com/fishaudio/fish-speech

Key Features

•Expressive text-to-speech model
•Natural-language emotion control
•Natural-language prosody control
•Available through Fish Audio app/API
•Open-source release linked from the official Fish Audio GitHub repository

Capabilities

•text-to-speech
•speech synthesis
•emotion control
•prosody control

Last updated Jul 31, 2026