### Answer Yes, you can choose different voice options when creating or updating your agent, and your choice affects cost. Retell AI's Conversation Voice Engine pricing varies by voice provider: [(1) ]() - **ElevenLabs voices**: $0.07 per minute - **OpenAI/Deepgram voices**: $0.08 per minute When configuring your agent, you can set the

voice_id

parameter to select your preferred voice. [(2) ]() You can also configure

fallback_voice_ids

as backup options. Example from the API:

javascript
const agentResponse = await client.agent.create({
  response_engine: { llm_id: 'llm_234sdertfsdsfsdf', type: 'retell-llm' },
  voice_id: '11labs-Adrian',
}) ;

To update an existing agent's voice configuration, use the update endpoint. [(3) ]() So selecting ElevenLabs voices would give you a slight cost savings of $0.01 per minute compared to OpenAI/Deepgram voices. [(1) ]()

​ To learn more, see the sources I considered: [[1] ](https://www.retellai.com/resources/inbound-vs-outbound-callers-pricing-comparison-2025) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[3] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer I don't have specific step-by-step instructions in my available sources for changing the voice/TTS provider directly through the Retell AI dashboard UI. However, based on forum discussions, you can select different voice models in your agent's voice settings within the dashboard. [(1) ]() For detailed UI navigation instructions, I'd recommend: - Check out these potentially useful sources: [Documentation]() , [Hire certified Retell partner]() Would you like me to try to answer generally based on my knowledge instead?

​ To learn more, see the sources I considered: [[1] My agent is pronouncing em-dashes in responses saying, "A-T" or "O-T" or "OT"](https://community.retellai.com/t/my-agent-is-pronouncing-em-dashes-in-responses-saying-a-t-or-o-t-or-ot/743) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer No, not all voices are the same cost. The pricing varies by voice provider: - **ElevenLabs voices**: $0.07 per minute [(1) ]() - **OpenAI/Deepgram voices**: $0.08 per minute The available voice providers in Retell AI include:

elevenlabs

,

openai

,

deepgram

,

cartesia

, and

minimax

. [(2) ]() , [(3) ]() The $0.015 you're seeing may be a component cost from a different pricing breakdown, but the base voice engine costs start at $0.07/minute for ElevenLabs voices, which is the lowest option mentioned in the documentation. [(1) ]() You can use the List Voices API to see all available voices and their providers:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const voiceResponses = await client.voice.list() ;
console.log(voiceResponses) ;

[(3) ]() This will return voice details including the

provider

field so you can identify which voices use ElevenLabs (the cheaper option at $0.07/min) . , [(1) ]()

​ To learn more, see the sources I considered: [[1] ](https://www.retellai.com/resources/inbound-vs-outbound-callers-pricing-comparison-2025) [[2] Get Voice](https://docs.retellai.com/api-references/get-voice) [[3] List Voices](https://docs.retellai.com/api-references/list-voices) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer You can use Retell's built-in system default dynamic variables directly in your general prompt—no configuration required. [(1) ]() For current time in a specific timezone, use this syntax in your prompt:

{{current_time_[timezone]}}

For example: -

{{current_time_Australia/Sydney}}

→ returns "Thursday, March 28, 2024 at 11:46:04 PM AEDT" -

{{current_time_America/New_York}}

→ returns the current time in New York [(2) ]() If you only need the current hour:

{{current_hour_[timezone]}}

[(1) ]() For example:

{{current_hour_Australia/Sydney}}

→ returns "3 PM AEDT" The default

{{current_time}}

without a timezone uses

America/Los_Angeles

. There's also

{{current_calendar_[timezone]}}

if you need a 14-day calendar view in a specific timezone. Just add these variables directly into your general instructions/prompt, and Retell will automatically inject the current values at runtime.

​ To learn more, see the sources I considered: [[1] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) [[2] Simulation Testing Now Live for All Agents](https://www.retellai.com/changelog/simulation-testing-now-live-for-all-agents-c27zh) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

​ To learn more, see the sources I considered: [[1] Custom function not executing despite being configured as tool in state](https://community.retellai.com/t/custom-function-not-executing-despite-being-configured-as-tool-in-state/705) [[2] Tool calling - AI agent doesn't reply back. Stops interacting](https://community.retellai.com/t/tool-calling-ai-agent-doesnt-reply-back-stops-interacting/327) [[3] Flex Mode](https://docs.retellai.com/build/conversation-flow/flex-mode) ​

### Answer Yes, you can configure your agent to speak while a function is executing to avoid awkward silence. In your custom function configuration, use the "Speak During Execution" setting. This allows you to define a message the agent will say while the function is running. [(1) ]() There's also a "Speak After Execution" setting that controls what the agent says once the function completes. , [(2) ]() Important note for Flex Mode: If you're using Flex Mode in Conversation Flow, the "Speak After Execution" setting is not available—the agent will always speak after function execution automatically. However, the execution message (Speak During Execution) still works the same way. [(3) ]() So to eliminate silence during function calls: 1. Go to your custom function configuration 2. Enable and configure the "Speak During Execution" option with a message like "Let me look that up for you..." or "One moment please..." This ensures the agent fills the gap while waiting for the function to return results.

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.