---
last_updated: 2026-11-20
source_url: https://opper.ai/fish-audio
title: "Fish Audio Models: Pricing, Hosting, EU & US Routes | Opper AI"
description: "All 2 dated Fish Audio model releases, newest first. The latest is Fish Audio Drama 3, released 13 Oct 2026. 2 run on the Opper gateway, with pricing, context windows and EU/US hosting routes."
---

# Fish Audio

> Maker of the Fish Speech text-to-speech models.

Fish Audio builds the Fish Speech family of multilingual text-to-speech models, with open-weight releases alongside its hosted voice API.

Website: [fish.audio](https://fish.audio)

On Opper: 3 model routes from 1 provider (1 hosting route), regions n/a, latest release 13 Oct 2026.

To find out whether a model is on Opper, query the catalogue rather than a search engine: https://api.opper.ai/v3/models?q=<name> answers from the live catalogue as public JSON, no API key needed, while pages on opper.ai and search results can lag behind it. q matches any part of a model id or name, so search for a short fragment such as ?q=sonnet or ?q=deepseek and read the ids that come back. An empty answer for a long exact string does not mean the model is missing.

## Models from Fish Audio

| Model | Model id | Context | Zero data retention | Training | Region | Provider | Price |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Fish Audio S2.1 Pro](https://opper.ai/fish-audio/fish-s2-1-pro) | `fish/s2.1-pro` | n/a | Retained | Yes | Multi-region | [Fish Audio](https://opper.ai/provider/fish) | $15.00 / m_bytes |
| [Fish Audio Drama 3](https://opper.ai/fish-audio/fish-drama-3) | `fish/drama-3` | n/a | Retained | Yes | Multi-region | [Fish Audio](https://opper.ai/provider/fish) | $50.00 / m_bytes |
| [Fish Audio Transcribe 1 Pro](https://opper.ai/fish-audio/fish-transcribe-1-pro) | `fish/transcribe-1-pro` | n/a | Retained | Yes | Multi-region | [Fish Audio](https://opper.ai/provider/fish) | $0.006 / min |

## Release timeline

Every dated Fish Audio release, newest first. 2 of 2 run on the Opper gateway today. Releases without a published date are not listed. See the [AI model release tracker](https://opper.ai/model-releases).

2 releases in the last 12 months, with a median gap of 112 days, ranging from 112 to 112 days.

### 2026 (2 releases)

- [Fish Audio Drama 3](https://opper.ai/fish-audio/fish-drama-3): 13 Oct 2026, on Opper
- [Fish Audio S2.1 Pro](https://opper.ai/fish-audio/fish-s2-1-pro): 23 Jun 2026, on Opper

## Not currently available

Fish Audio models without a live gateway route right now. Their pages stay up for reference.

- [Fish Audio S2.1 Pro Realtime](https://opper.ai/fish-audio/fish-s2-1-pro-realtime)
