# Fish Audio (/en/ai/platform/models/tts/fish-audio)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

> Documentation: Conversational AI.
> Documentation version: Preview.
> This document describes only this version. [Version index](/llms/doc-versions-convoai-guides-v2.txt).


Fish Audio provides text-to-speech (TTS) with flexible models and high-quality synthetic voices.

## Sample configuration

The following example shows how to configure Fish Audio as the agent's TTS when you create or update an agent. For a complete example, see [Create an agent and start a session](/en/ai/platform/get-started/start-stop-agent#create-an-agent).

Fish Audio supports BYOK only. It isn't available in managed mode. Store your Fish Audio API key in a secret set, and refer to it from the agent. For details, see [Use your own provider keys](/en/ai/platform/build/use-your-own-keys).

**Python SDK**

```python
from agora_agent import Agent, FishAudioTTS, secret_ref

# client is your configured Agora client
agent = (
    Agent(client=client)
    .with_stt(...)  # configure your ASR vendor
    .with_llm(...)  # configure your LLM vendor
    .with_tts(
        FishAudioTTS(
            key=secret_ref("support_prod", "fishaudio"),
            reference_id="<voice_model_id>",
            backend="speech-1.5",
        )
    )
)
```

**TypeScript SDK**

```ts
import { Agent, FishAudioTTS, secretRef } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(/* configure your ASR vendor */)
  .withLlm(/* configure your LLM vendor */)
  .withTts(
    new FishAudioTTS({
      key: secretRef('support_prod', 'fishaudio'),
      referenceId: '<voice_model_id>',
      backend: 'speech-1.5',
    }),
  );
```

**Go SDK**

```go
// client is your configured Agora client
agent := agentkit.NewAgent(client).
	WithStt( /* configure your ASR vendor */ ).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts(vendors.NewFishAudioTTS(vendors.FishAudioTTSOptions{
		Key:         agentkit.SecretRef("support_prod", "fishaudio"),
		ReferenceID: "<voice_model_id>",
		Backend:     "speech-1.5",
	}))
```

**REST API**

Set `credential.mode` to `byok` and `credential.fields.api_key` to a reference to your Fish Audio API key. In the following example, the key is stored as `fishaudio` in the `support_prod` set:

```json
"tts": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.fishaudio"
    }
  },
  "vendor": "fishaudio",
  "params": {
    "reference_id": "<voice_model_id>",
    "backend": "speech-1.5"
  }
}
```

## Key parameters

The `tts` block takes the following fields. In the SDKs, `FishAudioTTS` sets them from its options.

**tts**

**`vendor` (string) required**

Set to `fishaudio`.

**`credential` (object) required**

Set `mode` to `byok` and `fields.api_key` to a `$secrets.<set>.<key>` reference to your Fish Audio API key.

**`params` (object) required**

**`reference_id` (string) required**

The identifier of the voice model to use for speech synthesis.

**`backend` (string) required**

The backend model version to use. For example, `speech-1.5`.

> **Caution**
>
> The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in `params` are passed through directly to Fish Audio without validation. For a full list of supported options, refer to the [Fish Audio documentation](https://docs.fish.audio/sdk-reference/python/api-reference).

This integration is fully supported for use with the Conversational AI Platform. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.