https://retellai.com/?utm_source=discord&utm_medium=seo logo
Powered by
When the maximum call duration is reached, the cal...
# ❓・ai-evy-support
n
@AI Evy When the maximum call duration is reached, the call ends abruptly. Can we make this transition more natural? For example, by calling a function to play a closing message.
a
Thanks for tagging me @Nameless. I'll look through relevant sources and get back to you shortly.
### Answer Currently, when the 
max_call_duration_ms
setting is reached, the call ends with a hard hangup. [(1) ]() [(2) ]() This is an abrupt termination without a graceful closing message. Workaround Using Prompt Engineering: One approach discussed in the community is to add instructions in your agent's prompt to handle time limits gracefully. For example, you could include: [(3) ]() "The call should not exceed 10 minutes. If the conversation approaches the 10 minutes mark, gracefully summarize the key points, thank the lead for their time, and conclude the call efficiently by invoking the end_call function." This relies on the LLM being aware of call duration and proactively ending the call before the hard limit is reached. However, community feedback suggests this may not work reliably and could result in hallucinations. Current Limitations: Based on community discussions, there's currently no built-in feature to automatically trigger a function or play a closing message when 
max_call_duration_ms
is reached. [(4) ]() [(3) ]() The 
max_call_duration_ms
parameter (minimum 60,000 ms, maximum 7,200,000 ms, default 3,600,000 ms) will force end the call when reached. [(1) ]() [(2) ]() Recommendation: If you need a more graceful ending, consider implementing your own timing logic using webhooks to track call duration and t
rigger an end_call function with a closing message before the hard limit is reached. This would require external monitoring rather than relying on the built-in 
max_call_duration_ms
setting.
​ 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] Discord message from @micheldenizob on 2024-11-25](https://discord.com/channels/1186424376300679209/1186462578310910112/1310737566684942337) [[4] Control call duration consistently with a natural ending without using Max call duration which is abrupt](https://community.retellai.com/t/control-call-duration-consistently-with-a-natural-ending-without-using-max-call-duration-which-is-abrupt/299) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
Thanks for the follow-up, @Nameless. I'll get back to you soon.
n
@AI Evy Conversation flow: rigid mode with global node vs flex mode vs flex mode with global nodes
a
### Answer Here's a comparison of the three conversation flow approaches: Rigid Mode with Global Node: [(1) ]() - Standard conversation flow where nodes define specific logic and transitions - Global nodes can be enabled on specific nodes to allow transitions into that node from anywhere in the conversation [(2) ]() - When a node is marked as global, you must define the condition to transition into it [(3) ]() - Provides structured, predictable behavior with fine-grained control [(1) ]() - Each node has specific logic and outcomes Flex Mode: [(4) ]() - Combines conversation flow structure with single prompt flexibility - All nodes get converted to a single flex node when enabled at agent level - Compiles the flow into one structured prompt made of Tasks and available Tools - Agent navigates Tasks dynamically while following your global prompt - Stays on the flex node and behaves like a single prompt agent until reaching 'End Call' - Can easily switch context between different tasks - Node-level knowledge bases are ignored in Flex Mode Flex Mode with Global Nodes: - When enabled on a component (rather than agent level) , only that component's nodes are converted into a single prompt - The rest stays as standard conversation flow - This allows mixing flex behavior in specific parts while maintaining rigid structure elsewhere Key Differences: - Rigid mode evaluates transitions node-by-node; flex mode compiles everything into one prompt - Flex mode has significantly higher LLM costs due to larger token counts - Flex mode ignore
s "Speak After Execution" and "waitForResult" settings - For flows with more than 20 nodes, flex mode may degrade performance and increase hallucination risk
​ To learn more, see the sources I considered: [[1] Conversation Flow Overview](https://docs.retellai.com/build/conversation-flow/overview) [[2] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) [[3] Step 3: Add transition conditions](https://docs.retellai.com/build/conversation-flow/transition-condition) [[4] Flex Mode](https://docs.retellai.com/build/conversation-flow/flex-mode) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy retell API support edit of the prompt and showing the conversation flow from an external window?
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Based on the available sources, I can confirm that the Conversation Flow API is available for programmatic management. [(1) ]() API Support for Conversation Flows: The Conversation Flow API allows you to create and manage conversation flows programmatically, including: - Creating conversation flows - Listing conversation flows [(2) ]() - Managing nodes, edges, tools, and components Editing Prompts via API: The API supports modifying conversation flow configurations, including the 
global_prompt
field which applies to the entire conversation. You can update prompts and other settings programmatically through the API endpoints. Displaying Conversation Flow Externally: The API provides access to the full conversation flow structure, including: - Nodes (conversation, subagent, function, logic, end nodes) [(3) ]() - Edges and transition conditions - Components (reusable sub-flows) [(3) ]() [(4) ]() - Display positions for visual rendering [(2) ]() The API response includes 
begin_tag_display_position
and 
display_position
coordinates for nodes and notes, which you could use to render the conversation flow in an external window. Example Response Structure: The List Conversation Flows API returns data including node positions, edges, and the complete flow structure that could be visualized externally. However, the sources don't explicitly describe a dedicated "visualization export" endpoint or confirm whether third-party tools can directly render the flow diagram outside the Ret
ell dashboard.
​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] List Conversation Flows](https://docs.retellai.com/api-references/list-conversation-flows) [[3] Conversation Flow Overview](https://docs.retellai.com/build/conversation-flow/overview) [[4] 🚀 Conversation Flow Components are live!](https://community.retellai.com/t/conversation-flow-components-are-live/150) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy can we set dynamic variables based on caller id
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Yes, you can set dynamic variables based on caller ID using the Inbound Call Webhook. [(1) ]() How it works: For inbound calls, you can supply dynamic variables through the Inbound Call Webhook. The webhook receives information about the incoming call, including the caller's phone number (
from_number
) . [(2) ]() Implementation approach: 1. Set up an Inbound Call Webhook for your agent 2. When the webhook receives the call notification, extract the 
from_number
(caller ID) 3. Use the caller ID to look up relevant information in your database or CRM 4. Return the dynamic variables in the webhook response Example webhook response structure:
Copy code
json
{
  "call_inbound": {
    "dynamic_variables": {
        "caller_name": "John Doe"
    }
  }
}
[(3) ]() Available caller information: The system provides 
{{user_number}}
as a default system variable, which contains the user's phone number (from_number for inbound calls) . [(1) ]() You can use this in your webhook logic to determine which dynamic variables to set. Note: All values in 
retell_llm_dynamic_variables
must be strings.
​ To learn more, see the sources I considered: [[1] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) [[2] Register Phone Call](https://docs.retellai.com/api-references/register-phone-call) [[3] Dynamic Variables](https://discord.com/channels/1186424376300679209/1356680357084135558) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
Thanks for the follow-up, @Nameless. I'll get back to you soon.
n
@AI Evy can i play a voiced script (an audio file) in certain flow
a
​ To learn more, see the sources I considered: [[1] Conversation Flow Overview](https://docs.retellai.com/build/conversation-flow/overview) [[2] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) [[3] Code Node](https://docs.retellai.com/build/conversation-flow/code-node) ​
### Answer Based on the available sources, I don't have specific documentation about playing audio files directly within a conversation flow. However, the sources do describe several node types that could potentially be used in your flow: [(1) ]() [(2) ]() [(3) ]() Conversation Nodes allow you to set either: - **Prompt**: Write a prompt for the agent to dynamically generate what to say - **Static Sentence**: Agent will say a fixed sentence first [(2) ]() Code Nodes execute JavaScript code when the agent enters them, and you can configure Speak During Execution where the agent says something while the code runs. [(3) ]() The sources don't explicitly mention playing pre-recorded audio files or integrating audio playback into the conversation flow. For a definitive answer about playing voiced scripts or audio files at specific points in your conversation flow, I'd recommend checking the full documentation or reaching out to support. Would you like a general answer based on my knowledge instead, or would you prefer to explore other conversation flow capabilities that are documented?
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy how to set up the extraction of caller id?
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer To extract caller ID for inbound calls, you need to set up an Inbound Webhook at the phone number level. [(1) ]() [(2) ]() Setup Steps: 1. Configure the Inbound Webhook URL in your phone number settings [(1) ]() 2. Your webhook endpoint will receive a POST request with the caller information Request Payload Structure: The webhook receives the caller ID in the 
from_number
field:
Copy code
json
{
  "event": "call_inbound",
  "call_inbound": {
    "agent_id": "agent_12345",
    "agent_version": 1,
    "from_number": "+12137771234",
    "to_number": "+12137771235"
  }
}
Key Fields: - `from_number`: The caller's phone number (always present in payload) - `to_number`: The number being called (always present in payload) - `agent_id`: If the number has an inbound agent ID set - `agent_version`: If the number has an inbound agent version set Webhook Security: The webhook can be verified using your Retell API Key to ensure it comes from Retell AI. The webhook has a 10-second timeout and will retry up to 3 times if no success status (2xx) is received. Using the Caller ID: Once you extract 
from_number
, you can use it to look up customer information in your database/CRM and return dynamic variables in your webhook response.
​ To learn more, see the sources I considered: [[1] Inbound webhook](https://docs.retellai.com/features/inbound-call-webhook) [[2] Receive calls](https://docs.retellai.com/deploy/inbound-call) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy how to set an Inbound Call Webhook in conversation flow
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
Using Variables in Conversation Flow: The dynamic variables you return (like 
customer_name
) can be referenced in your conversation flow nodes using the 
{{customer_name}}
syntax. [(2) ]() Important Notes: - The webhook has a 10-second timeout [(1) ]() - It will retry up to 3 times if no success status (2xx) is received - The webhook can be verified using your Retell API Key - This is part of your number configuration and works for purchased or imported numbers
### Answer ### Answer The Inbound Call Webhook is configured at the phone number level, not within the conversation flow itself. [(1) ]() Here's how to set it up: Configuration Location: 1. Go to your phone number configuration page 2. Enable the "Inbound Webhook" setting 3. Enter your webhook endpoint URL How It Works with Conversation Flow: Once configured, the webhook is triggered when an inbound call is received, before the conversation flow begins. The webhook receives caller information and can return dynamic variables that will be available throughout your conversation flow. [(1) ]() [(2) ]() Webhook Request Payload: Your endpoint will receive:
Copy code
json
{
  "event": "call_inbound",
  "call_inbound": {
    "agent_id": "agent_12345",
    "agent_version": 1,
    "from_number": "+12137771234",
    "to_number": "+12137771235"
  }
}
[(1) ]() Webhook Response to Set Dynamic Variables: Return dynamic variables that your conversation flow can access:
Copy code
json
{
  "call_inbound": {
    "override_agent_id": "agent_12345",
    "override_agent_version": 1,
    "dynamic_variables": {
      "customer_name": "John Doe"
    },
    "metadata": {
      "random_id": "12345"
    }
  }
}
​ To learn more, see the sources I considered: [[1] Inbound webhook](https://docs.retellai.com/features/inbound-call-webhook) [[2] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy what file type is support in retell knowledge base
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer ### Answer Retell AI's Knowledge Base supports the following file formats: [(1) ]() - .bmp - .csv - .doc - .docx - .eml - .epub - .heic - .html - .jpeg - .jpg - .png - .md - .msg - .odt - .org - .p7s - .pdf - .ppt - .pptx - .rst - .rtf - .tiff - .txt - .tsv - .xls - .xlsx - .xml File Limits: - Maximum 25 files per knowledge base - Each file limited to 50MB - For CSV, TSV, XLS, and XLSX files: maximum 1000 rows and 50 columns Note: While .jpg and .jpeg are technically the same format, both are accepted by the platform. [(2) ]() Best Practice: Prefer .md (Markdown) files over .txt for better chunking and retrieval accuracy. [(1) ]()
​ To learn more, see the sources I considered: [[1] Knowledge Base](https://docs.retellai.com/build/knowledge-base) [[2] Knowledge Base: Supported file formats](https://discord.com/channels/1186424376300679209/1315890673655873628) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy if i can export the call flow as json, can i import to replace existing call flow
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Yes, you can export and import conversation flows using JSON through the Retell AI API. [(1) ]() [(2) ]() [(3) ]() [(4) ]() Export (Get) a Conversation Flow: Use the Get Conversation Flow API to retrieve the complete JSON structure: [(4) ]()
Copy code
javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: process.env['RETELL_API_KEY'],
}) ;
const conversationFlowResponse = await client.conversationFlow.retrieve('conversation_flow_id') ;
console.log(conversationFlowResponse.conversation_flow_id) ;
Import (Update) to Replace Existing Flow: Use the Update Conversation Flow API to replace an existing conversation flow with your JSON data: [(3) ]()
Copy code
javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: process.env['RETELL_API_KEY'],
}) ;
const conversationFlowResponse = await client.conversationFlow.update('conversation_flow_id') ;
console.log(conversationFlowResponse.conversation_flow_id) ;
Create New Flow from JSON: Alternatively, create a new conversation flow from your exported JSON: [(2) ]()
Copy code
javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: process.env['RETELL_API_KEY'],
}) ;
const conversationFlowResponse = await client.conversationFlow.create({
 model_choice: { model: 'gpt-4.1', type: 'cascading' },
 nodes: [
 {
 id: 'start',
 instruction: { text: 'Greet the customer and ask how you can help them.', type: 'prompt' },
 type: 'conversation',
 },
 ],
 start_speaker: 'agent',
}) ;
console.log(conversationFlowResponse.conversation_flow_id) ;
The JSON structure includes all conversation flow properties like nodes, edges, tools, components, global_prompt, and model_choice. [(1) ]() [(3) ]() [(4) ]()
​ To learn more, see the sources I considered: [[1] List Conversation Flows](https://docs.retellai.com/api-references/list-conversation-flows) [[2] Create Conversation Flow](https://docs.retellai.com/api-references/create-conversation-flow) [[3] Update Conversation Flow](https://docs.retellai.com/api-references/update-conversation-flow) [[4] Get Conversation Flow](https://docs.retellai.com/api-references/get-conversation-flow) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy can i do this without api
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Based on the available sources, exporting and importing conversation flows without using the API is not directly documented. [(1) ]() [(2) ]() [(3) ]() The Conversation Flow API was introduced to enable programmatic creation and management of conversation flows. [(3) ]() Community discussions indicate that conversation flow management was initially only available through the dashboard, not via API. [(4) ]() [(5) ]() Currently, the documented methods for exporting/importing conversation flows all involve API calls using the SDK. [(1) ]() [(2) ]() Dashboard capabilities mentioned in sources: - You can build and edit conversation flows visually in the dashboard [(3) ]() - The platform has an "Import/Export Agents" feature that allows exporting and importing agents between organizations However, the sources don't explicitly confirm whether the agent import/export feature includes the full conversation flow structure or if it works without API access. For a definitive answer about dashboard-only export/import of conversation flows (without API) , I'd recommend: - Checking the dashboard's import/export functionality directly - Visiting [Documentation]() - Visiting [Hire certified Retell partner]() Would you like a general answer based on my knowledge instead?
​ To learn more, see the sources I considered: [[1] Create Conversation Flow](https://docs.retellai.com/api-references/create-conversation-flow) [[2] List Conversation Flows](https://docs.retellai.com/api-references/list-conversation-flows) [[3] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[4] API for conversation flow agents](https://discord.com/channels/1186424376300679209/1329434473661599754) [[5] Is there no way to use conversional flow via the API?](https://discord.com/channels/1186424376300679209/1385350640427073706) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy retell support multi language conversion only what langue’s
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer I don't have specific documentation listing all supported languages for Retell AI's multilingual capabilities. However, based on the available sources: What the sources confirm: Retell AI supports 31+ languages with ElevenLabs integration. [(1) ]() How multilingual support works: The language setting is configured for the Speech-to-Text (STT) layer to understand and convert speech to text, while the voice setting (from providers like ElevenLabs) handles the Text-to-Speech (TTS) layer. [(2) ]() Community discussions indicate: - English is fully supported for production use cases - Some European languages like French and Spanish have been mentioned [(1) ]() - Middle Eastern languages have been tested by community members [(3) ]() - Indian/Indic languages require custom integration (like Reverie STT/TTS) [(4) ]() [(5) ]() To use a specific language: You can configure the language in your agent settings and customize the begin message and prompts in your desired language. The LLM model you use should also support that language. [(3) ]() For a complete and current list of all supported languages, I recommend: - Visiting [Documentation]() - Visiting [Hire certified Retell partner]() Would you like a general answer based on my knowledge instead?
​ To learn more, see the sources I considered: [[1] Bland AI Review: Real Costs, Latency Issues & Better Option | Retell AI](https://www.retellai.com/blog/bland-ai-reviews) [[2] custom llm - other languages](https://discord.com/channels/1186424376300679209/1242562712450367591) [[3] Discord message from @swimleftproducts on 2024-07-08](https://discord.com/channels/1186424376300679209/1186462578310910112/1259694829407965197) [[4] Integrate Reverie STT and TTS for Indic Language Support](https://discord.com/channels/1186424376300679209/1400343548599079043) [[5] Integration with Google TTS for more languages?](https://discord.com/channels/1186424376300679209/1300975625041084476) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy I mean auto switch voicebot languages, how to do? And what languages do it support
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Retell AI supports multilingual mode that enables automatic language switching during conversations. [(1) ]() Supported Languages for Multilingual Switching: The platform supports seamless switching between: English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch (using nova 3) . How to Enable Multilingual Mode: Based on community discussions, you can enable multilingual mode in regions with bilingual or multilingual users, allowing the bot to switch between languages seamlessly. [(2) ]() Additional Language Support: Retell AI also added support for 10 more languages: Romanian, Danish, Finnish, Greek, Indonesian, Norwegian, Slovak, Swedish, Bulgarian, and Hungarian. [(1) ]() The platform has expanded to support 50+ languages total, including recently added languages like Arabic, Persian, Serbian, Swahili, Tamil, and Urdu. [(3) ]() Important Notes: - Community feedback indicates that code-switching (switching languages mid-conversation) requires true multilingual ASR capabilities. [(2) ]() - Some users have reported that when selecting a single language (like Hindi or Spanish) , transcription becomes weaker for the second language in bilingual scenarios. - The multilingual ASR is designed to handle language detection and switching, though the exact configuration steps for enabling this feature aren't fully detailed in the available sources. For specific implementation guidance on enabling automatic language switching for your use case, I recommend: - Visiting [Documentation]() - Visiting
[Hire certified Retell partner]() Would you like a general answer based on my knowledge instead?
​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Multilingual or Bilingual Transcription](https://discord.com/channels/1186424376300679209/1230269781161279508) [[3] Smarter Understanding, Clearer Calls: Retell’s ASR Just Got a Major Upgrade | Retell AI](https://www.retellai.com/blog/retell-asr) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy code switching support switch among what languages
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer Retell AI's multilingual mode supports seamless code-switching between English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch (using nova 3) . [(1) ]() Additionally, Retell AI has expanded support to include Romanian, Danish, Finnish, Greek, Indonesian, Norwegian, Slovak, Swedish, Bulgarian, and Hungarian. The platform now supports 50+ languages total, including recently added languages like Arabic, Persian, Serbian, Swahili, Tamil, and Urdu. [(2) ]() How Auto Language Detection Works: Retell agents have the option to detect and automatically switch to 10+ languages including English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, Dutch, and more. [(3) ]() Important Note: Community discussions indicate that true code-switching (switching languages mid-conversation) requires multilingual ASR capabilities. [(4) ]() Some users have reported that when selecting a single language, transcription becomes weaker for the second language in bilingual scenarios.
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] OpenAI 4.1, Version Control, and More Languages Support](https://www.retellai.com/changelog/openai-4-1-version-control-and-more-languages-support) [[2] Smarter Understanding, Clearer Calls: Retell’s ASR Just Got a Major Upgrade | Retell AI](https://www.retellai.com/blog/retell-asr) [[3] The 8 Best AI Voice Agents with Multilingual Support | Retell AI](https://www.retellai.com/blog/8-leading-multilingual-ai-voice-agents) [[4] Multilingual or Bilingual Transcription](https://discord.com/channels/1186424376300679209/1230269781161279508) ​
Thanks for the follow-up, @Nameless. I'll get back to you soon.
n
@AI Evy what is the required format for json file for importing to simulation function
a
### Answer Based on the available sources, the exact JSON schema for importing test cases into the Simulation feature isn't fully documented. [(1) ]() However, a community member shared a helpful workaround: create a couple of test cases manually in the dashboard with all the features you want to use (
message has been deleted
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy it shows Sync failed Request failed with status code 400
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer A *400 error (Bad Request) * typically indicates a problem with the request format or parameters you're sending. [(1) ]() Common causes for 400 errors in Retell AI: 1. Function parameters format issue - The parameters must follow the function calling format. Check that your JSON structure matches the expected schema. 2. Invalid request format - Ensure you're following the API reference correctly. [(2) ]() 3. Authentication or permissions issue - Verify your API key has the correct scope and permissions for the operation. [(3) ]() Troubleshooting steps: 1. Check your function parameters - Review the last section of your request payload to ensure parameters follow the proper format. [(1) ]() 2. Verify API endpoint - Confirm you're using the correct endpoint URL and that your API key has access to the specific organization/resource. [(3) ]() 3. Review request body - Ensure all required fields are included and properly formatted according to the API documentation. 4. Check API key scope - The API key on one account may have different permissions than another, which could cause 404 or 400 errors. For function calling specifically, refer to this guide for the proper parameter format: [(1) ]() If the issue persists: - Visit [Documentation]() - Visit [Hire certified Retell part
ner]() Can you share more details about what operation you're attempting (Knowledge Base sync, API call, function configuration, etc.) ? That would help narrow down the specific cause.
​ To learn more, see the sources I considered: [[1] Status code 400](https://discord.com/channels/1186424376300679209/1441197468174782577) [[2] Delete Conversation Flow](https://docs.retellai.com/api-references/delete-conversation-flow) [[3] Question about API's](https://discord.com/channels/1186424376300679209/1404590446214385705) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
n
@AI Evy is there a way to let the voicebot determine. Whether the caller is woman or man (based on voice pattern
a
Thanks for the follow-up, @Nameless. I'll get back to you soon.
### Answer I don't have information about voice-based gender detection capabilities in the available sources. The sources cover speech processing technologies like ASR (speech-to-text conversion) , sentiment analysis (detecting emotional tone) , and voice activity detection, but none explicitly mention gender identification or voice pattern analysis for determining caller demographics. [(1) ]() [(2) ]() [(3) ]() For a definitive answer about whether Retell AI supports voice-based gender detection or demographic analysis features, I recommend: - Visiting [Documentation]() - Visiting [Hire certified Retell partner]() Would you like a general answer based on my knowledge instead?
​ To learn more, see the sources I considered: [[1] Automatic Speech Recognition (ASR)](https://www.retellai.com/glossary/automatic-speech-recognition-asr) [[2] Sentiment Analysis](https://www.retellai.com/glossary/sentiment-analysis) [[3] Speech Processing](https://www.retellai.com/glossary/speech-processing) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
PreviousNext
Powered by