> ## Documentation Index
> Fetch the complete documentation index at: https://docs.simli.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Simli Auto

> Create interactive AI avatars with just a few API calls

## Overview

Simli Auto is our managed API and provides streamlined way to integrate conversational AI agents into your applications with minimal setup.

Simli Auto now supports [custom LLMs](/api-reference/endpoint/simli-auto/customLLM), but if you need even more composability (such as making your custom voice bot), check out the [Simli API Reference](/simli-sdks) instead.

For changing the interaction languages, you can look at the support list on [Deepgram's website](https://developers.deepgram.com/docs/models-languages-overview)

## API Endpoints

There are two ways to build with Simli Auto. The recommended way for most people is using session tokens to authenticate:

* **`POST /auto/token`**: Creates a new session token for authentication. Requires your Simli API key and optionally a TTS API key.
* **`POST /auto/start/{agent_id}`**: Starts a session using token in the header for authentication (see API reference).

An alternative way to start a session without creating a token first is to use this endpoint:

* **`POST /auto/start/configurable`**: Initializes a new end-to-end interactive session with an AI avatar. Configure TTS provider, language, and other session parameters.

For conversation transcripts:

* **`GET /auto/transcript/{sessionId}`**: Retrieves the conversation transcript for a specific session if transcript generation was enabled.

## Getting Started

To start using the Simli Auto API, you'll need:

1. A Simli API key
2. (Optional) API keys for your preferred TTS provider
3. (Optional) Custom LLM configuration if not using the default model

### Quick Start

Here's a basic flow to get started:

1. Create a session token:

```bash theme={null}
POST /auto/token
{
  "simliAPIKey": "your-api-key",
  "ttsAPIKey": "your-tts-api-key"  // Optional
}
```

2. Start an end-to-end session:

```bash theme={null}
POST /auto/start/configurable
{
  "apiKey": "your-api-key",
  "faceId": "your-face-id",
  "ttsProvider": "ElevenLabs"
  "language": "en",
  "createTranscript": false
}
```

### Using Custom LLMs

Simli Auto supports integration with any OpenAI-compatible LLM API. To use your own LLM:

```json theme={null}
{
	"customLLMConfig": {
		"model": "your-model-name",
		"baseURL": "https://your-llm-api-endpoint.com",
		"llmAPIKey": "your-llm-api-key"
	}
}
```

### Session Configuration

You can customize various session parameters:

* `maxSessionLength`: Maximum duration of the session in seconds (default: 3600)
* `maxIdleTime`: Maximum idle time before session timeout in seconds (default: 300)
* `systemPrompt`: Custom prompt to define the AI's behavior
* `firstMessage`: Initial message from the AI when session starts

## Best Practices

1. **Session Management**
   * Keep track of session tokens and handle expiration appropriately
   * Configure idle times based on your use case

2. **Resource Optimization**
   * Use appropriate batch sizes for audio processing
   * Handle session cleanup when no longer needed

3. **Error Handling**
   * Implement proper error handling for API responses
   * Monitor session status and handle timeouts gracefully

## Rate Limits and Quotas

Please refer to your API plan for specific rate limits and quotas. Ensure your application handles rate limiting appropriately to maintain optimal performance.

## Next Steps

* Explore the detailed API reference for each endpoint
* Check out our example implementations
* Join our community for support and updates

For more detailed information about specific endpoints and features, navigate through the API reference sections.