### Answer --- There are two key features in Retell AI that can help with your brand name pronunciation issue: ## 1. Pronunciation Dictionary You can set up a pronunciation guide for specific words in the Speech Settings. [(1) ]() [(2) ]() This allows you to define exactly how the agent should pronounce specific brand names using phonetic notation (IPA alphabet) . Via the API, you can configure this using the

pronunciation_dictionary

parameter: [(3) ]()

json
"pronunciation_dictionary": [
  {
    "word": "actually",
    "alphabet": "ipa",
    "phoneme": "ˈæktʃuəli"
  }
]

You would replace the example with your brand names and their correct IPA phonemes. ## 2. Boosted Keywords Additionally, you can use Boosted Keywords to help with recognition accuracy—this biases the speech-to-text model toward certain words like brand names, making them easier to recognize when users say them. [(1) ]() [(2) ]() [(4) ]() You can add up to 100 custom keywords. [(4) ]() ## Where to Configure Both settings are found under Speech Settings in your agent configuration: - For single/multi-prompt agents: [Step 2: Configure the basic settings]() [(1) ]() - For conversation flow agents: [Step 1: Configure global settings]() [(2) ]() For 200+ brands, you may want to use the API to programmatically update the

pronunciation_dictionary

and

boosted_keywords

arrays. [(3) ]()

​ 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] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) [[3] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[4] Increase transcription accuracy](https://docs.retellai.com/reliability/wrong-transcript) ​

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

### Answer Yes, you can add pronunciations in bulk using the API. The

pronunciation_dictionary

parameter accepts an array of pronunciation entries, so you can include all 200+ brand names in a single API call when creating or updating your agent. [(1) ]() [(2) ]() Here's the structure you would use:

json
"pronunciation_dictionary": [
  {
    "word": "BrandName1",
    "alphabet": "ipa",
    "phoneme": "phonetic_pronunciation_1"
  },
  {
    "word": "BrandName2",
    "alphabet": "ipa",
    "phoneme": "phonetic_pronunciation_2"
  }
]

You can programmatically build this array with all your brand names and their IPA phonemes, then send it via the [Update Voice Agent]() API endpoint. [(1) ]() Important notes: - The pronunciation dictionary currently only works with English agents using 11Labs voices with the

eleven_turbo_v2

voice model selected. [(3) ]() - You can use

ipa

or

cmu

as the phonetic alphabet. - For finding correct IPA phonemes, you can use tools like [tophonetics.com]() or the [CMU pronouncing dictionary]() .

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] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[3] Mispronunciation of a brand name](https://community.retellai.com/t/mispronunciation-of-a-brand-name/741) ​

### Answer You can control the speaking pace using the voice_speed setting in your agent configuration. [(1) ]() ## Voice Speed Setting The

voice_speed

parameter controls the speed of voice, with values ranging from **0.5 to 2**: - Lower values (e.g., 0.5) = slower speech - Higher values (e.g., 2) = faster speech - Default value is 1 ## Where to Configure In the dashboard, you can find this under Speech Settings when configuring your agent. [(2) ]() Via the API, you can set it like this:

json
"voice_speed": 0.8

[(1) ]() ## Dynamic Voice Speed There's also an

enable_dynamic_voice_speed

option—when set to

true

, it enables dynamic voice speed adjustment based on the user's speech rate and conversation context.

json
"enable_dynamic_voice_speed": true

## Responsiveness Setting Additionally, you can adjust responsiveness (values 0-1) to control how quickly the agent responds. Reducing responsiveness by 0.1 adds 0.5 seconds of agent wait time, which can be useful when talking to folks who need more time to process information. [(2) ]()

​ To learn more, see the sources I considered: [[1] Get Agent Versions](https://docs.retellai.com/api-references/get-agent-versions) [[2] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) ​

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