> ## Documentation Index
> Fetch the complete documentation index at: https://docs.retellai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Step 2: Configure the basic settings
> Configure your AI agent with language models, voice settings and advanced customization.
Follow these steps to configure the fundamental settings for your agent, optimizing it for your specific business requirements.
We recommend starting with GPT-4.1, which offers an optimal balance of:
* Response quality
* Latency
* Cost-effectiveness
1. Open the voice selection dropdown menu:
2. Listen to the available voice samples and note the voice ID of your preferred option:
**Custom Voices**: You can also add voices from the ElevenLabs community by clicking "Add custom voice". Learn more in our [voice configuration guide](/build/voice).
**Voice Speed**: You can adjust the agent's speaking speed using the Voice Speed slider (ranging from 0.5x to 2.0x) in the voice settings popover. If you check "Dynamically adjust based on user input", the agent will automatically adapt its speaking speed to match the user's pace during the call. It does this by tracking the user's words per minute and gradually shifting its own speed to align, making the conversation feel more natural. When dynamic voice speed is enabled, the user can also explicitly ask the agent to speak faster or slower, and the agent will adjust on the fly.
Define how your agent starts conversations:
* **User-First**: Agent waits for user input
* **Agent-First**: Agent initiates the conversation
* Set a fixed welcome message
* Use prompts to guide the agent's opening message
### More Settings
You can further customize your agent by setting the following settings:
Here's where you specify the agent's persona, identity, guardrails, etc. This set of text will be available in every node, and will influence all response generation.
Here's where you can supply contexts to agent via documents, urls, texts. Read more at [Knowledge Base Guide](/build/knowledge-base).
Here's a lot of options that allow you to finetune how your agent interacts with user.
* Background sound: select a background sound that plays throughout the whole call to mimic an environment like call center, making the conversation more humanlike and engaging.
* Responsiveness: how responsive the agent is. Set it lower if you want the agent to wait longer before responding, which can be useful when talking to folks like the elderly. The lower the value, the more wait time is added before the agent responds. You can also check "Dynamically adjust based on user input" to let the agent automatically tune its response timing during the call. When enabled, the agent observes how quickly the user speaks and adjusts accordingly — slower speakers get more patient response timing, while faster speakers get quicker responses.
* Interruption Sensitivity: how fast the agent gets interrupted by user interruptions. Set it lower if you want agent to be more resilient to background speech.
* Backchanneling: Set up how often and what words the agent uses to acknowledge users.
* Boosted Keywords: Provides some biases towards certain words, making it easier to get recognized. Common ones are brand names, people's names, etc.
* Speech Normalization: convert entities like date, currency, numbers into plain words, which can help prevent issues where audio generated was not pronouncing those right.
* Reminder frequency: how often the agent will remind the user when user is inactive.
* Pronunciation: set up pronunciation guide for specific words.
Here's a couple of settings that's more call operation related.
* Voicemail related settings: set up voicemail detection and what to do when voicemail is detected. See more at [Handle Voicemail](/build/handle-voicemail).
* End call on silence: set up if user is active for a certain amount of time, the call will be ended.
* Call duration: set up maximum duration of the call.
* Pause before speaking: For the beginning of the call, if agent speaks first, it will wait for the configured duration before speaking, useful to handle scenarios when user is still picking up the phone.
Probably set up later, read more at [Post Call Analysis Guide](/features/post-call-analysis-overview).
Here's where you can set up whether to opt out sensitive data storage, and configure webhook settings for receiving call related events.
### Video Tutorial
See community templates in [docs](https://docs.google.com/document/d/1hx6hdTEjAR4y4xXZ7RLMH2byQNVW1ABxC8S4FwvTx_Y/edit?tab=t.0#heading=h.wf5bktkelope)
## Next Steps
Once you've configured these basic settings, your agent is ready for basic interactions. To enhance its capabilities, proceed to [adding capabilities by using function calling](/build/single-multi-prompt/function-calling).
2. Listen to the available voice samples and note the voice ID of your preferred option:
**Custom Voices**: You can also add voices from the ElevenLabs community by clicking "Add custom voice". Learn more in our [voice configuration guide](/build/voice).
**Voice Speed**: You can adjust the agent's speaking speed using the Voice Speed slider (ranging from 0.5x to 2.0x) in the voice settings popover. If you check "Dynamically adjust based on user input", the agent will automatically adapt its speaking speed to match the user's pace during the call. It does this by tracking the user's words per minute and gradually shifting its own speed to align, making the conversation feel more natural. When dynamic voice speed is enabled, the user can also explicitly ask the agent to speak faster or slower, and the agent will adjust on the fly.
