---
last_updated: 2026-11-21
source_url: https://opper.ai/fish-audio/fish-s2-1-pro
title: "Fish Audio S2.1 Pro by Fish Audio"
description: "Fish Speech S2.1 Pro, Fish Audio's multilingual text-to-speech and voice cloning model covering 83 languages from one model, with roughly 90ms time to first audio for live voice agents."
---

# Fish Audio S2.1 Pro

By [Fish Audio](https://opper.ai/fish-audio).

Released 23 Jun 2026 · [Announcement](https://fish.audio/blog/s2-1-pro-free-api/) · [All Fish Audio releases](https://opper.ai/model-releases/fish-audio)

Fish Speech S2.1 Pro, Fish Audio's multilingual text-to-speech and voice cloning model covering 83 languages from one model, with roughly 90ms time to first audio for live voice agents.

## Available routes

Fish Audio S2.1 Pro runs on 1 route through the Opper gateway. Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=fish%2Fs2.1-pro.

| Provider | Model id | Region | Zero data retention | Training | Price |
| --- | --- | --- | --- | --- | --- |
| [Fish Audio](https://opper.ai/provider/fish) | `fish/s2.1-pro` | Multi-region | Retained | Yes | $15.00 / m_bytes |

## Key info

- Model id: `fish/s2.1-pro`
- Input: Text
- Output: Audio
- Features: none listed
- Pricing: $15.00 / m_bytes
- Billing: Per m_bytes
- Released: 23 Jun 2026

## Pricing

Usage-based pricing, billed per m_bytes, not by token.

| Variant | Price |
| --- | --- |
| Standard | $15.00 / m_bytes |

## Data handling per route

Each route hosting Fish Audio S2.1 Pro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Fish Audio — Multi-region

Content is retained: used for training by default. Trained on customer data by default. GLOBAL; unknown.

- Zero data retention: Retained: used for training by default.
- Training: Trained on customer data by default.
- Transfer mechanism: unknown

Verified by Opper on 2026-10-29.

## Get started

Call Fish Audio S2.1 Pro through the Opper gateway with one API key. Text-to-speech models run on POST /v3/audio/speech, which returns the audio in the response. The OpenAI SDK works too, through /v3/compat/audio/speech.

See the [Opper audio guide](https://docs.opper.ai/build/multimodal/audio) and the [Opper multimodal skill](https://skills.opper.ai/opper-multimodal/SKILL.md).

Fish Audio S2.1 Pro is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai/opper-multimodal/SKILL.md Generate speech with Fish Audio S2.1 Pro
```

### Or call it directly

cURL:

```bash
curl -s https://api.opper.ai/v3/audio/speech \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fish/s2.1-pro",
    "input": "Hello from Opper."
  }' \
  | jq -r '.audio.b64_json' | base64 --decode > speech.mp3
```

OpenAI:

```javascript
import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const speech = await client.audio.speech.create({
  model: "fish/s2.1-pro",
  input: "Hello from Opper.",
});
await writeFile("speech.mp3", Buffer.from(await speech.arrayBuffer()));
```

## Use Fish Audio S2.1 Pro in your apps

Pick your tool to see how to run it on Fish Audio S2.1 Pro through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/fish-s2-1-pro)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/fish-s2-1-pro)
- [Codex](https://opper.ai/apps/codex/fish-s2-1-pro)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/fish-s2-1-pro)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/fish-s2-1-pro)
- [Aider](https://opper.ai/apps/aider/fish-s2-1-pro)
- [Goose](https://opper.ai/apps/goose/fish-s2-1-pro)
- [Droid](https://opper.ai/apps/droid/fish-s2-1-pro)
- [OpenCode](https://opper.ai/apps/opencode/fish-s2-1-pro)
- [Pi](https://opper.ai/apps/pi/fish-s2-1-pro)
- [OpenClaw](https://opper.ai/apps/openclaw/fish-s2-1-pro)
- [Hermes](https://opper.ai/apps/hermes/fish-s2-1-pro)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/fish-s2-1-pro)
- [OmniRoute](https://opper.ai/apps/omniroute/fish-s2-1-pro)
- [Cursor](https://opper.ai/apps/cursor/fish-s2-1-pro)
- [Cline](https://opper.ai/apps/cline/fish-s2-1-pro)
- [Continue](https://opper.ai/apps/continue/fish-s2-1-pro)
- [Kilo Code](https://opper.ai/apps/kilo-code/fish-s2-1-pro)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/fish-s2-1-pro)
- [Zed](https://opper.ai/apps/zed/fish-s2-1-pro)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/fish-s2-1-pro)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/fish-s2-1-pro)
- [n8n](https://opper.ai/apps/n8n/fish-s2-1-pro)
- [LibreChat](https://opper.ai/apps/librechat/fish-s2-1-pro)
- [Open WebUI](https://opper.ai/apps/open-webui/fish-s2-1-pro)
- [See all apps](https://opper.ai/apps)

## Other models from Fish Audio

- [Fish Audio Drama 3](https://opper.ai/fish-audio/fish-drama-3)
- [Fish Audio Transcribe 1 Pro](https://opper.ai/fish-audio/fish-transcribe-1-pro)
