# Mistral (/en/ai/platform/models/tts/mistral)

> 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).


Mistral provides enterprise-grade AI voice generation with text-to-speech (TTS) models.

## Sample configuration

The following example shows how to configure Mistral 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).

Mistral supports BYOK only. It isn't available in managed mode. Store your Mistral 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, MistralTTS, 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(
        MistralTTS(
            api_key=secret_ref("support_prod", "mistral"),
            model="voxtral-mini-tts-2603",
            voice="<your_mistral_voice>",
        )
    )
)
```

**TypeScript SDK**

```ts
import { Agent, MistralTTS, 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 MistralTTS({
      apiKey: secretRef('support_prod', 'mistral'),
      model: 'voxtral-mini-tts-2603',
      voice: '<your_mistral_voice>',
    }),
  );
```

**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.NewMistralTTS(vendors.MistralTTSOptions{
		APIKey: agentkit.SecretRef("support_prod", "mistral"),
		Model:  "voxtral-mini-tts-2603",
		Voice:  "<your_mistral_voice>",
	}))
```

**REST API**

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

```json
"tts": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.mistral"
    }
  },
  "vendor": "mistral",
  "params": {
    "model": "voxtral-mini-tts-2603",
    "voice": "<your_mistral_voice>"
  }
}
```

## Key parameters

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

**tts**

**`vendor` (string) required**

Set to `mistral`.

**`credential` (object) required**

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

**`params` (object) optional**

**`model` (string) optional**

The TTS model to use, for example `voxtral-mini-tts-2603`.

**`voice` (string) optional**

The voice identifier to use.

> **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 Mistral without validation. For a full list of supported options, refer to the [Mistral documentation](https://docs.mistral.ai/api/endpoint/audio/speech).

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.