---
title: "How to Switch from OpenAI Voice to Fish Audio"
description: "Switch OpenAI text-to-speech to Fish Audio while keeping the OpenAI SDK. Point it at AllModels, then change the model and voice."
canonical: "https://allmodels.io/guides/how-to-switch-from-openai-voice-to-fish-audio"
markdown: "https://allmodels.io/guides/how-to-switch-from-openai-voice-to-fish-audio.md"
author: "AllModels"
datePublished: "2026-07-30"
dateModified: "2026-07-30"
---

# How to Switch from OpenAI Voice to Fish Audio

Keep the OpenAI SDK. Point it at AllModels, then replace the model and voice. Your speech-generation call stays the same.

## The short answer

1. Use your AllModels API key and set the SDK base URL to `https://api.allmodels.io/oai`.
2. Set the model to `fish/s2-1-pro` and replace `FISH_VOICE_ID` with a [Fish voice ID](https://allmodels.io/model?model=fish%2Fs2-1-pro#voices).

> AllModels is an independent service and is not affiliated with, endorsed by, or sponsored by OpenAI, ElevenLabs, Fish Audio, or Cartesia.

## Code

These examples generate an MP3 response. The provider migration only changes the client configuration, model, and voice.

### JavaScript

Before — OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY
});

const speech = await client.audio.speech.create({
  model: "gpt-4o-mini-tts",
  voice: "OPENAI_VOICE",
  input: "Hello from my application",
  response_format: "mp3"
});
```

After — Fish Audio through AllModels:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseURL: "https://api.allmodels.io/oai"
});

const speech = await client.audio.speech.create({
  model: "fish/s2-1-pro",
  voice: "FISH_VOICE_ID",
  input: "Hello from my application",
  response_format: "mp3"
});
```

### Python

Before — OpenAI:

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["OPENAI_API_KEY"],
)

with client.audio.speech.with_streaming_response.create(
    model="gpt-4o-mini-tts",
    voice="OPENAI_VOICE",
    input="Hello from my application",
    response_format="mp3",
) as response:
    response.stream_to_file("speech.mp3")
```

After — Fish Audio through AllModels:

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ALLMODELS_API_KEY"],
    base_url="https://api.allmodels.io/oai",
)

with client.audio.speech.with_streaming_response.create(
    model="fish/s2-1-pro",
    voice="FISH_VOICE_ID",
    input="Hello from my application",
    response_format="mp3",
) as response:
    response.stream_to_file("speech.mp3")
```

## Keep using the OpenAI SDK

Switching providers through AllModels is intentionally simple: keep the SDK and request flow you already use, point the client at AllModels, then choose a different model and voice.

The compatible OpenAI SDK surface supports:

- [text-to-speech and streamed speech responses](https://docs.allmodels.io/openai/text-to-speech)
- [file transcription](https://docs.allmodels.io/openai/transcription)
- [realtime transcription](https://docs.allmodels.io/openai/realtime)

Read the [complete OpenAI SDK compatibility guide](https://docs.allmodels.io/openai) for setup details, supported methods, and current limitations.

## About Fish Audio S2.1 Pro

Fish Audio launched S2.1 Pro alongside a $52 million seed announcement. The company says the model can clone a voice from five seconds of audio and offers word-level control over emotion, intonation, and pacing.

Fish Audio also claims S2.1 Pro is twice as fast as Cartesia and costs one sixth as much as ElevenLabs, and names HeyGen, LiveKit, Retell, Sanas, and OpenArt as production users. Treat those as provider-reported comparisons and test quality, latency, and cost against your own workload.

- [Visit Fish Audio](https://fish.audio/)
- [Read Fish Audio’s S2.1 Pro announcement](https://x.com/FishAudio/status/2082152596739862853)

## Common migration questions

### Do I need to replace the OpenAI SDK?

No. Keep the installed SDK and its speech method. AllModels exposes a compatible base URL for it.

### Can I reuse my OpenAI voice?

No. Choose a voice from the [Fish Audio S2.1 Pro voice list](https://allmodels.io/model?model=fish%2Fs2-1-pro#voices), then replace `FISH_VOICE_ID` with its ID.

### Can I switch providers again later?

Yes. Keep the AllModels base URL and API key, then change the model and voice to another supported provider.

## Continue

- [Browse Fish Audio models](https://allmodels.io/models?provider=fish)
- [Read the AllModels documentation](https://docs.allmodels.io)
- [View the canonical HTML guide](https://allmodels.io/guides/how-to-switch-from-openai-voice-to-fish-audio)