### Answer To make your agent sound more human with its tonality, you can configure several voice and speech settings: Voice Emotion Set the

voice_emotion

parameter to control the emotional tone of your agent's voice [(1) ]() . Available emotions include:

calm

,

sympathetic

,

happy

,

sad

,

angry

,

fearful

, and

surprised

. This feature is currently supported for Cartesia and Minimax TTS providers . Voice Temperature Adjust

voice_temperature

(ranging from 0-2) to control voice stability . Lower values produce more stable speech, while higher values create more variant speech generation . The default is 1 . Voice Speed Use

voice_speed

(ranging from 0.5-2) to control speaking pace . You can also enable

enable_dynamic_voice_speed

to automatically adjust the agent's speed based on the user's speech rate and conversation context [(1) ]() [(2) ]() . Backchannel Enable

enable_backchannel

to have the agent interject with phrases like "yeah" or "uh-huh" to signify interest and engagement . You can control frequency with

backchannel_frequency

(0-1) and customize the words used with

backchannel_words

. Background Sound Add

ambient_sound

to mimic realistic environments like

coffee-shop

,

convention-hall

, or

call-center

. This makes conversations feel more natural and humanlike [(2) ]() . Responsiveness Adjust

responsiveness

(0-1) and enable

enable_dynamic_responsiveness

to control how quickly the agent responds based on user speech patterns [(1) ]() [(2) ](

configure-basic-settings) .

​ To learn more, see the sources I considered: [[1] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[2] Step 2: Configure the basic settings](https://docs.retellai.com/build/single-multi-prompt/configure-basic-settings) ​

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

### Answer You can set voice emotion and temperature when creating or updating your agent through the API [(1) ]() [(2) ]() . Voice Emotion Set the

voice_emotion

parameter to control the emotional tone. Available options are:

calm

,

sympathetic

,

happy

,

sad

,

angry

,

fearful

,

surprised

, or

null

. This feature is currently supported for Cartesia and Minimax TTS providers . Voice Temperature Set the

voice_temperature

parameter with a value ranging from 0 to 2 . Lower values (closer to 0) produce more stable speech, while higher values (closer to 2) create more variant speech generation . The default value is 1 . Example Implementation

javascript
const agentResponse = await client.agent.update('16b980523634a6dc504898cda492e939', {
  agent_name: 'Jarvis',
}) ;

[(1) ]() To set these parameters, you would add them to your agent configuration object alongside other settings like

agent_name

. According to a Discord discussion, voice temperature controls the pitch/tone of the voice (e.g., making it more enthusiastic) , while model temperature controls agent creativity in following the script [(3) ]() .

​ To learn more, see the sources I considered: [[1] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[2] Get Voice Agent](https://docs.retellai.com/api-references/get-agent) [[3] Discord message from @.zacharythomas on 2025-01-27](https://discord.com/channels/1186424376300679209/1186462578310910112/1333472363236556801) ​

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

Thanks for the follow-up, @✯. I'll get back to you soon.

​ To learn more, see the sources I considered: [[1] Step 2: Configure the basic settings](https://docs.retellai.com/build/single-multi-prompt/configure-basic-settings) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[3] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) ​

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