Create agent
ElevenLabs Create Agent is a powerful tool that enables users to build customized AI agents leveraging advanced large language models and speech synthesis. Designed for flexibility, it supports multiple LLMs, voice configurations, and conversation parameters to tailor agent interactions.
Features
- Supports a wide range of state-of-the-art LLMs including GPT-4, Gemini, and Claude series for versatile AI capabilities.
- Customizable agent prompts and names for easy identification and specific task focus.
- Configurable temperature and max token settings to control response creativity and length.
- Built-in text-to-speech functionality with selectable voices and TTS models for natural audio output.
- Advanced conversation management including max duration, turn timeout, and first message customization for seamless user experience.
Benefits
- Create highly personalized AI agents tailored to unique business or personal needs.
- Enhance user engagement through natural, conversational AI powered by top-tier language models.
- Optimize response quality by adjusting parameters like temperature and max tokens.
- Integrate voice-based interactions seamlessly with multiple voice IDs and TTS models.
- Save development time with a ready-to-use, flexible API supporting varied AI interaction scenarios.
Description
Create an agent in Eleventlabs. See the documentation
Parameters
11 parameters
| Name | Type | Description |
|---|---|---|
| promptrequired | string | The prompt for the agent |
| name | string | A name to make the agent easier to find |
| llm | enum | The LLM to query with the prompt and the chat history |
| temperature | string | The temperature for the LLM. Defaults to |
| maxTokens | integer | If greater than 0, maximum number of tokens the LLM can predict |
| firstMessage | string | If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion. |
| language | string | Language of the agent - used for ASR and TTS. Defaults to |
| maxDurationSeconds | integer | The maximum duration of a conversation in seconds. Defaults to |
| turnTimeout | string | Maximum wait time for the user’s reply before re-engaging the user. Defaults to |
| voiceId | string | The voice ID to use for TTS |
| ttsModelId | enum | The model to use for TTS |
