# Gradium (/en/ai/platform/models/tts/gradium)

> 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).


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

## Sample configuration

The following example shows how to configure Gradium 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).

Gradium supports BYOK only. It isn't available in managed mode. Store your Gradium 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, GradiumTTS, 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(
        GradiumTTS(
            api_key=secret_ref("support_prod", "gradium"),
            url="wss://api.gradium.ai/api/speech/tts",
            model_name="default",
            voice_id="<your_gradium_voice_id>",
            sample_rate=16000,
        )
    )
)
```

**TypeScript SDK**

```ts
import { Agent, GradiumTTS, 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 GradiumTTS({
      apiKey: secretRef('support_prod', 'gradium'),
      url: 'wss://api.gradium.ai/api/speech/tts',
      modelName: 'default',
      voiceId: '<your_gradium_voice_id>',
      sampleRate: 16000,
    }),
  );
```

**Go SDK**

```go
// client is your configured Agora client
sampleRate := vendors.SampleRate16kHz
agent := agentkit.NewAgent(client).
	WithStt( /* configure your ASR vendor */ ).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts(vendors.NewGradiumTTS(vendors.GradiumTTSOptions{
		APIKey:     agentkit.SecretRef("support_prod", "gradium"),
		URL:        "wss://api.gradium.ai/api/speech/tts",
		ModelName:  "default",
		VoiceID:    "<your_gradium_voice_id>",
		SampleRate: &sampleRate,
	}))
```

**REST API**

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

```json
"tts": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.gradium"
    }
  },
  "vendor": "gradium",
  "url": "wss://api.gradium.ai/api/speech/tts",
  "params": {
    "model_name": "default",
    "voice_id": "<your_gradium_voice_id>",
    "sample_rate": 16000
  }
}
```

## Key parameters

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

**tts**

**`vendor` (string) required**

Set to `gradium`.

**`credential` (object) required**

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

**`url` (string) optional**

The WebSocket endpoint for streaming TTS output. For example, `wss://api.gradium.ai/api/speech/tts`.

**`params` (object) required**

**`model_name` (string) optional**

The TTS model to use. For example, `default`.

**`voice_id` (string) optional**

The voice identifier to use.

**`sample_rate` (number) optional**

The audio sample rate in Hz. For example, `16000`.

> **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 Gradium without validation. For a full list of supported options, refer to the [Gradium documentation](https://docs.gradium.ai/guides/text-to-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.