### Answer Based on the available documentation, I can see that the

voice_id

field accepts voice IDs from supported providers, and the

voice_model

field supports specific models including options like

speech-02-turbo

and

speech-2.8-turbo

for MiniMax voices. [(1) ]() However, I don't have specific documentation about the voice ID format

Hebrew_male_1_v1

or the full list of available MiniMax voice IDs in my sources. Here's what you can try: 1. Check the Dashboard – The documentation states: "Find list of available voices and their preview in Dashboard." The Retell AI Dashboard should show all available voice IDs you can use. 2. Use the API – When creating or updating an agent via API, you set the

voice_id

directly:

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

If the voice ID isn't appearing in the platform, it may not be a supported MiniMax voice in Retell AI's current integration. I'd recommend checking the Dashboard voice library for the exact MiniMax voice IDs available, or reaching out for support if you believe this voice should be accessible. Check out these potentially useful sources: - [Create Voice Agent]()

​ To learn more, see the sources I considered: [[1] 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.

### Answer Based on the available documentation, I don't have specific information about Hebrew voice support or language restrictions for Cartesia voices in Retell AI. Here's what I can share about TTS providers: TTS Provider Options: - ElevenLabs – Best for natural sounding voices and niche accent needs [(1) ]() - Cartesia – Natural sounding with stronger spelling accuracy - MiniMax – Strongest spelling, most consistent tone, and great for Asian languages Language Support: The

language

field in agent configuration supports

he-IL

(Hebrew) for speech recognition. [(2) ]() However, I don't have documentation confirming which TTS providers support Hebrew voice output or any specific restrictions on Hebrew voices with Cartesia. Regarding speech normalization: Currently, for non-MiniMax TTS providers, speech normalization is only supported for English, Spanish, French, and German. Other languages result in no modification. [(3) ]() Since this appears to be a language/voice availability limitation, I'd recommend reaching out for assistance: - Visit [Documentation]() - Visit [Hire certified Retell partner]() Would you like me to provide a general answer based on broader voice AI knowledge?

​ To learn more, see the sources I considered: [[1] TTS provider comparison](https://docs.retellai.com/build/tts-provider-comparison) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[3] Normalize text for speech](https://docs.retellai.com/build/normalize-text) ​

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

@AI Evy If using the API, can i set TTS and STT models as i wish regardless of what you support in the UI platform?

### Answer Based on the available sources, I don't have specific documentation about whether the API allows you to set arbitrary TTS (Text-to-Speech) or STT (Speech-to-Text/ASR) models beyond what's supported in the UI platform. What I can confirm from the sources: TTS and ASR are core components of Retell AI's architecture: - *Automatic Speech Recognition (ASR) * converts spoken words into text in real time [(1) ]() - *Text-to-Speech (TTS) * turns AI-generated text responses into natural-sounding speech For optimization, Retell AI recommends: - Change to a faster LLM to reduce response time [(2) ]() - Change to a faster TTS for quicker audio output However, the sources don't explicitly state whether the API provides access to TTS/STT models that aren't available in the Dashboard UI, or whether you can use completely custom/external models. I'd recommend checking the official documentation or reaching out for clarification: - Visit [Documentation]() - Visit [Hire certified Retell partner]() Would you like a general answer based on my broader knowledge of voice AI APIs?

​ To learn more, see the sources I considered: [[1] Speech Processing](https://www.retellai.com/glossary/speech-processing) [[2] Performance-related configurations and noticeable latency during live calls](https://community.retellai.com/t/performance-related-configurations-and-noticeable-latency-during-live-calls/747) ​

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