### Answer For sales use cases with specific logic flows like lead qualification, Retell AI provides built-in state management through Multi-Prompt Agents that can handle this without requiring external frameworks like LangGraph. [(1) ]() [(2) ]() ## When to Use Retell's Native State Management Retell recommends using Conversation Flow agents when you need: [(1) ]() - **Multiple decision branches**: More than 3-4 conditional paths - **Tool coordination**: Using 5+ different functions/tools - **State management**: Tracking multiple variables throughout the conversation - **Reliability concerns**: Single prompt shows inconsistent behavior The benefits of Conversation Flow include: - Each node focuses on one specific task - Deterministic tool calling and transitions - Easier to debug and optimize individual steps - More predictable agent behavior ## How Multi-Prompt Agents Work Multi-prompt agents organize conversations into a structured tree of states, each with its own focused prompt and behavior. [(2) ]() For example, you can create states like "information_collection" and "appointment_booking", where each state has: [(3) ]() [(4) ]() [(5) ]() - Its own

state_prompt

- Specific tools available in that state - Defined edges for transitions to other states ## Prompting for Reliability For reliable state transitions in sales flows, you should: [(1) ]() 1. Define clear triggers

- Specify exact conditions for tool usage and state transitions in your prompts, referencing tools by their exact names 2. Use trigger words - List specific words/phrases that should trigger transitions 3. Define sequences - Specify when tools should be called in order 4. Set boundaries - Clarify when NOT to call certain tools or transition states **Bottom line**: For lead qualification with specific logic flows, Retell's native Multi-Prompt Agent or Conversation Flow architecture is designed exactly for this purpose and should handle it reliably without needing LangGraph. The key is structuring your states properly and writing explicit transition criteria in your prompts. [(1) ]() [(2) ]()

​ To learn more, see the sources I considered: [[1] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) [[2] How to Deploy Conversational AI | Retell AI](https://www.retellai.com/blog/how-to-deploy-conversational-ai) [[3] Update Retell LLM](https://docs.retellai.com/api-references/update-retell-llm) [[4] List Retell LLMs](https://docs.retellai.com/api-references/list-retell-llms) [[5] Create Retell LLM](https://docs.retellai.com/api-references/create-retell-llm) ​

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

### Answer Based on the available sources, here's what I can share about TTS pricing: ## Retell AI TTS Pricing Retell AI charges $0.07+ per minute for AI Voice Agents in their pay-as-you-go model. [(1) ]() [(2) ]() This bundled pricing includes TTS costs along with other components like speech recognition and LLM processing. [(1) ]() When using premium voice models within Retell AI: [(3) ]() - **ElevenLabs voices**: $0.07 per minute - **OpenAI/Deepgram voices**: $0.08 per minute ## General TTS Provider Pricing The sources mention typical TTS pricing ranges across providers: [(1) ]() [(2) ]() Text-to-Speech (TTS) costs typically range from $0.016–$0.048 per minute [(1) ]() , with variations based on: - Neural voice models vs. standard voices - Custom voice cloning capabilities - Emotional tone and speaking style variations Specific provider examples mentioned: [(2) ]() - **Google Cloud TTS**: ~$80 for 5,000 minutes ($16 per 1M characters) - **Azure Cognitive Services**: ~$70 for 5,000 minutes ($16 per 1M characters) - **AWS Polly**: ~$60 for 5,000 minutes ($16 per 1M characters) - **ElevenLabs**: $0.30 per 1K characters (premium quality) - **OpenAI**: $15 per 1M characters TTS ## Cartesia Regarding Cartesia specif

​ To learn more, see the sources I considered: [[1] ](https://www.retellai.com/resources/voice-ai-platform-pricing-comparison-2025) [[2] ](https://www.retellai.com/resources/inbound-vs-outbound-callers-pricing-comparison-2025) [[3] ](https://www.retellai.com/resources/sub-second-latency-voice-assistants-benchmarks) [[4] adding cartesia.ai as a TTS option?](https://discord.com/channels/1186424376300679209/1265558920668250207) ​

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