**please add an apostrophe (`'`) before the plus sign.**
## How to extract call details in structured JSON format? By defining any relevant information you wish to extract from the conversation, you can use `Extraction prompt`. Post every call, you'll get this data in the [Execution](/api-reference/executions/get_execution) payload in `extracted_data` key. ### Example ```text extraction prompt theme={"system"} user_name : Yield the name of the user. payment_mode : If user is paying by cash, yield cash. If they are paying by card yield card. Else yield NA payment_date: yield payment date by the user in YYYY-MM-DD format ``` ```json response theme={"system"} ... ... "extracted_data": { "user_name": "Bruce", "payment_mode": "paypal, "payment_date": "2024-12-30" }, ... ... ``` ## What can I extract from calls? You can extract any information discussed during the conversation: * **Customer information**: Names, email addresses, phone numbers * **Appointment details**: Dates, times, preferences * **Lead qualification data**: Budget, timeline, decision-maker status * **Payment information**: Payment method, amount, date * **Product preferences**: Sizes, colors, quantities * **Feedback and sentiment**: Satisfaction scores, complaints, compliments ## Next steps Ready to implement data extraction? Configure extraction prompts in your agent or explore related features: * Use [context variables](/using-context) to pre-fill known information * Access extraction data via the [Executions API](/api-reference/executions/get_execution) * Integrate with [custom functions](/tool-calling/custom-function-calls) for real-time actions * Set up [batch calling](/batch-calling) with personalized context per call For advanced use cases, combine extraction with [multi-agent workflows](/multi-agent-prompt) for complex conversations. # Understanding Latency Metrics in Voice AI Executions Source: https://www.bolna.ai/docs/call-latencies Comprehensive guide to analyzing latency in Bolna Voice AI. Explore performance insights across transcription, LLM processing, and speech synthesis. ## Introduction Bolna provides detailed latency metrics for every Voice AI execution, allowing you to monitor and optimize the performance of your conversational AI agents. These metrics help you understand where time is being spent in the conversation pipeline and identify potential bottlenecks that may affect user experience. The latency data is included in the execution payload when you fetch execution details via the [Get Execution API](/api-reference/executions/get_execution). This data provides granular timing information across all major components of the voice AI pipeline.
(e.g., `in` for India, `us` for United States) | ## Transcriber Metrics The transcriber component converts spoken audio into text. This section tracks how quickly speech is being transcribed. ```json theme={"system"} { "transcriber": { "time_to_connect": 226, "turns": [ { "turn": 1, "turn_latency": [ { "sequence_id": 1, "audio_to_text_latency": 20.12128, "text": "hello who is there" }, { "sequence_id": 2, "audio_to_text_latency": 19.96126, "text": "hello who is this" } ] } ] } } ``` ### Field Definition | Field | Type | Description | | ------------------------------- | --------------- | ------------------------------------------------------------------------ | | `time_to_connect` | `integer` | Time (ms) to establish connection with the transcriber provider. | | `turns` | `array