# Fish Audio 发布 S2.1 Pro，5 秒语音克隆

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-30 09:42
- AIHOT 分数：47
- AIHOT 链接：https://aihot.virxact.com/items/cms6v6zdq0h2grohzyelyrgds
- 原文链接：https://x.com/rohanpaul_ai/status/2082643005916553468

## AI 摘要

Fish Audio 完成 5200 万美元种子轮融资，并推出 S2.1 Pro 语音模型。该模型可从 5 秒音频克隆声音，速度比 Cartesia 快 2 倍，成本仅为 Eleven Labs 的 1/6，响应延迟约 90ms。它支持 83+ 种语言和 15000+ 自然语言控制指令，允许开发者通过 [whisper]、[laugh] 等提示词实现单词级情感与语调控制。

## 正文

So much work is happening on the voice layer of AI.

Fish Audio just launched S2.1 Pro and completed a $52M Seed round.

Voice cloning now has crossed a threshold， this new S2.1 Pro can clone a voice from 5 seconds of audio.

2x faster than Cartesia & 1/6th the cost of Eleven Labs. ~90ms response， fast enough for real conversation

They report 15，000+ natural-language controls， 83+ languages， 8M users， and $21M in annual recurring revenue.

Developers can place instructions such as 【whisper】， 【laugh】， or 【professional broadcast tone】 beside specific words instead of selecting preset emotions.

### 引用推文

> Fish Audio：Today we've raised $52M Seed and we are announcing the public launch of S2.1 Pro. >It can clone a voice from 5 seconds of audio >2x faster than Cartesia & 1/6th...