# rapida.ai documentation

## Docs

- [Rapida Voice AI Platform](https://doc.rapida.ai/introduction/overview.md): The open-source platform for building, deploying, and operating production voice AI systems at scale.
- [Assistants](https://doc.rapida.ai/assistants/overview.md): Understand what an assistant is, how it is structured, how a live conversation flows through it, and how to iterate safely in production.
- [Create and Configure an Assistant](https://doc.rapida.ai/assistants/create-assistant.md): Build a production-ready voice AI assistant — from prompt definition to runtime configuration, tools, knowledge, and deployment.
- [Provider Model (Prompt Executor)](https://doc.rapida.ai/assistants/create-new-version.md): Step-by-step guide to creating a new version of an existing AI assistant
- [AgentKit — Custom LLM Backend](https://doc.rapida.ai/assistants/agentkit.md): Create an AgentKit assistant in Rapida, connect your own gRPC backend, and go live quickly with production-safe patterns.
- [Scale AgentKit backends](https://doc.rapida.ai/assistants/agentkit/scaling.md): Benchmark, horizontally scale, route, and operate customer-owned AgentKit gRPC backends.
- [Assistant Prompt Templating](https://doc.rapida.ai/assistants/prompt-templating.md): How to use runtime prompt variables correctly, with variable meaning tables and production-ready examples.
- [Experience](https://doc.rapida.ai/assistants/configuration/experience.md): Define shared session behavior for assistant deployments.
- [Authentication](https://doc.rapida.ai/assistants/configuration/authentication.md): Configure conversation-time authentication from Rapida Console.
- [Listen](https://doc.rapida.ai/assistants/configuration/listen.md): Configure how Rapida captures, cleans, detects, and transcribes user speech.
- [Speech-to-Text](https://doc.rapida.ai/assistants/speech-to-text.md): Configure STT providers, credentials, models, language, and transcription tuning for Rapida voice assistants.
- [Noise cancellation](https://doc.rapida.ai/assistants/noise-cancellation.md): Configure background noise removal and understand how it affects VAD, STT, and voice assistant latency.
- [Voice Activity Detection (VAD)](https://doc.rapida.ai/assistants/voice-activity-detection.md): Understand VAD providers, their parameters, and how to choose the right one for your voice AI assistant.
- [End of Speech Detection (EOS)](https://doc.rapida.ai/assistants/end-of-speech.md): Understand End of Speech providers, their parameters, and how to choose the right one for your voice AI assistant.
- [Speak](https://doc.rapida.ai/assistants/configuration/speak.md): Configure how Rapida turns assistant responses into spoken output.
- [Text-to-Speech](https://doc.rapida.ai/assistants/text-to-speech.md): Configure TTS providers, voices, languages, pronunciation, ambient audio, and speech delivery for Rapida voice assistants.
- [Phone Call Deployment](https://doc.rapida.ai/voice-deployment-options/phone.md): Deploy your AI assistant on inbound and outbound phone calls with full telephony, STT, and TTS configuration.
- [Web Widget Deployment](https://doc.rapida.ai/voice-deployment-options/web-widget.md): Embed an AI voice and chat widget on any website with a single script tag.
- [Web App / SDK Deployment](https://doc.rapida.ai/voice-deployment-options/web-app.md): Integrate your AI assistant into any React application via the Rapida SDK or REST API.
- [WhatsApp Deployment](https://doc.rapida.ai/voice-deployment-options/whatsapp.md): Connect your AI assistant to WhatsApp Business for automated conversational interactions at scale.
- [Adding Knowledge Sources](https://doc.rapida.ai/assistants/knowledge/add-knowledge.md): Configure knowledge sources for your assistant to enhance information retrieval
- [Tools](https://doc.rapida.ai/assistants/introduction-to-tools.md): Enhance your assistant with knowledge retrieval, API calls, endpoint calls, call transfer, call hold, and conversation-ending actions.
- [Knowledge Retrieval Tool](https://doc.rapida.ai/assistants/tools/add-knowledge-tool.md): Configure and use the Knowledge Retrieval Tool to access information from your knowledge base
- [Endpoint (LLM Call) Tool](https://doc.rapida.ai/assistants/tools/add-endpoint-tool.md): Configure and use the Endpoint (LLM Call) Tool to make API calls to language models
- [API Call Tool](https://doc.rapida.ai/assistants/tools/add-api-tool.md): Configure and use the API Call Tool to make external API requests
- [Transfer Call Tool](https://doc.rapida.ai/assistants/tools/add-transfer-call-tool.md): Configure and use the Transfer Call Tool to hand an active phone call to another phone number or SIP target.
- [Put On Hold Tool](https://doc.rapida.ai/assistants/tools/add-put-on-hold-tool.md): Configure and use the Put On Hold Tool to pause phone calls for a specified duration
- [End of Conversation Tool](https://doc.rapida.ai/assistants/tools/add-end-of-conversation-tool.md): Configure and use the End of Conversation Tool to signal the end of a conversation
- [Overview](https://doc.rapida.ai/assistants/analysis/overview.md): Step-by-step guide to setting up analysis for your AI assistant
- [Create Analysis for Assistant](https://doc.rapida.ai/assistants/analysis/create-analysis.md): Step-by-step guide to setting up analysis for your AI assistant
- [Update Analysis for Assistant](https://doc.rapida.ai/assistants/analysis/update-analysis.md): Step-by-step guide to update analysis for your AI assistant
- [Overview](https://doc.rapida.ai/assistants/webhook/overview.md): Configure webhooks to receive call, conversation, and WebRTC events
- [Setting Up Webhooks](https://doc.rapida.ai/assistants/webhook/create-webhook.md): Configure webhooks to receive call, conversation, and WebRTC events
- [Update Webhook](https://doc.rapida.ai/assistants/webhook/update-webhook.md): Configure webhooks to receive call, conversation, and WebRTC events
- [Assistant Telemetry](https://doc.rapida.ai/assistants/telemetry.md): Configure telemetry providers, understand required fields, and use telemetry records for debugging and optimization.
- [Overview](https://doc.rapida.ai/knowledge/overview.md): Enhance your AI applications with powerful knowledge integration
- [Create knowledge](https://doc.rapida.ai/knowledge/create-knowledge.md): Learn how to create a new knowledge base in the system
- [Add new document](https://doc.rapida.ai/knowledge/add-new-document.md): A simple guide to adding documents to your knowledge
- [Manage Document Chunks](https://doc.rapida.ai/knowledge/manage-document-chunk.md): Learn how to manage and enhance document chunks for improved knowledge base performance
- [Overview](https://doc.rapida.ai/endpoint/overview.md): Seamlessly integrate LLMs into your application with powerful, flexible endpoints
- [Create endpoint](https://doc.rapida.ai/endpoint/create-endpoint.md): Endpoints allow you to integrate Large Language Models (LLMs) into your application, providing a powerful interface for AI-driven functionalities.
- [Create new version](https://doc.rapida.ai/endpoint/create-new-version.md): Quick guide to updating your existing endpoint with a new version.
- [Monitoring & debugging](https://doc.rapida.ai/endpoint/monitor-endpoint-performance.md): The endpoint dashboard provides a detailed view of your deployment's performance and activity. Here's how to use it effectively for monitoring and debugging:
- [Assistant Conversation Logs](https://doc.rapida.ai/activity/conversation-logs.md): Monitor and improve your AI assistant interactions in Rapida
- [LLM Logs](https://doc.rapida.ai/activity/llm-logs.md): Monitor and analyze Language Model (LLM) interactions in the Rapida platform
- [Webhook Logs](https://doc.rapida.ai/activity/webhook-logs.md): Monitor and analyze webhook interactions in the Rapida platform
- [OpenAI](https://doc.rapida.ai/integrations/llm/openai.md): OpenAI is a leading AI research and deployment company, known for its advanced language models like GPT-3 and GPT-4.
- [Anthropic](https://doc.rapida.ai/integrations/llm/anthropic.md): Anthropic is an AI research company known for its advanced language models, including the Claude series.
- [Azure OpenAI](https://doc.rapida.ai/integrations/llm/azure-openai.md): Azure OpenAI Service provides REST API access to OpenAI's powerful language models including the GPT-4 series.
- [Gemini / Google AI Studio](https://doc.rapida.ai/integrations/llm/gemini.md): Gemini is Google's latest family of large language models that can understand and generate text, images, and more.
- [Google AI](https://doc.rapida.ai/integrations/llm/google-ai.md): Google AI provides advanced language models and AI capabilities through a unified API.
- [Google Vertex AI](https://doc.rapida.ai/integrations/llm/google-vertex-ai.md): Google Vertex AI is a fully-managed, unified AI development platform that provides access to Google's advanced models with enterprise features.
- [Cohere](https://doc.rapida.ai/integrations/llm/cohere.md): Cohere is an AI company that provides large language models and NLP tools for developers and businesses.
- [Mistral](https://doc.rapida.ai/integrations/llm/mistral.md): Mistral specializes in creating fast, secure, open-source large language models with excellent performance-to-cost ratio.
- [Hugging Face](https://doc.rapida.ai/integrations/llm/huggingface.md): Hugging Face provides a wide range of open-source models and AI capabilities through their Inference API.
- [AWS Bedrock](https://doc.rapida.ai/integrations/llm/bedrock.md): AWS Bedrock provides a fully managed service that offers a choice of high-performing foundation models from leading AI companies through a single API.
- [VoyageAI](https://doc.rapida.ai/integrations/llm/voyageai.md): VoyageAI is an AI company that provides advanced language models and AI solutions for various applications.
- [Custom LLM](https://doc.rapida.ai/integrations/llm/custom.md): Connect Rapida to an OpenAI-compatible or custom LLM endpoint.
- [Deepgram](https://doc.rapida.ai/integrations/stt/deepgram.md): Deepgram provides advanced speech-to-text and text-to-speech capabilities powered by AI.
- [AssemblyAI](https://doc.rapida.ai/integrations/stt/assemblyai.md): AssemblyAI provides advanced speech-to-text with AI-powered audio intelligence features.
- [Google Speech Service](https://doc.rapida.ai/integrations/stt/google-speech-service.md): Google Speech Service provides advanced speech-to-text and text-to-speech capabilities powered by Google Cloud.
- [Azure Cognitive Services](https://doc.rapida.ai/integrations/stt/azure-speech-service.md): Azure Cognitive Services Speech-to-Text provides real-time and batch transcription in 100+ languages.
- [OpenAI Whisper](https://doc.rapida.ai/integrations/stt/openai-whisper.md): OpenAI Whisper is a state-of-the-art speech recognition model with broad language support and high accuracy.
- [AWS Transcribe](https://doc.rapida.ai/integrations/stt/aws-transcribe.md): Amazon Transcribe is a fully managed automatic speech recognition (ASR) service that makes it easy to add speech-to-text capabilities to applications.
- [Cartesia](https://doc.rapida.ai/integrations/stt/cartesia.md): Cartesia provides advanced voice AI solutions with both speech-to-text and text-to-speech capabilities.
- [Rev.ai](https://doc.rapida.ai/integrations/stt/revai.md): Rev.ai provides highly accurate speech recognition powered by deep learning, with real-time and asynchronous transcription options.
- [Speechmatics](https://doc.rapida.ai/integrations/stt/speechmatics.md): Speechmatics delivers highly accurate, language-inclusive speech recognition with real-time and batch processing capabilities.
- [Sarvam AI](https://doc.rapida.ai/integrations/stt/sarvam.md): Sarvam AI provides speech-to-text and text-to-speech solutions with strong support for Indian languages.
- [Groq STT](https://doc.rapida.ai/integrations/stt/groq.md): Groq provides ultra-fast speech-to-text via an OpenAI Whisper-compatible API powered by its LPU inference engine.
- [NVIDIA STT](https://doc.rapida.ai/integrations/stt/nvidia.md): NVIDIA provides enterprise-grade automatic speech recognition via the NVCF API.
- [Custom Speech-to-Text](https://doc.rapida.ai/integrations/stt/custom.md): Configure a custom WebSocket or HTTP speech-to-text provider with credentials, audio settings, query parameters, request rules, response rules, and the Rapida DSL.
- [ElevenLabs](https://doc.rapida.ai/integrations/tts/elevenlabs.md): ElevenLabs provides state-of-the-art text-to-speech with natural-sounding AI voices and advanced voice customization.
- [Deepgram Text-to-Speech](https://doc.rapida.ai/integrations/tts/deepgram.md): Deepgram's text-to-speech service provides ultra-realistic voice synthesis with natural-sounding output.
- [Azure Cognitive Services](https://doc.rapida.ai/integrations/tts/azure-speech-service.md): Azure Cognitive Services Text-to-Speech provides natural-sounding voice synthesis with multiple languages and voices.
- [Google Text-to-Speech](https://doc.rapida.ai/integrations/tts/google-speech-service.md): Google Cloud Text-to-Speech provides natural-sounding voice synthesis powered by advanced neural networks.
- [OpenAI TTS](https://doc.rapida.ai/integrations/tts/openai-tts.md): OpenAI Text-to-Speech delivers natural-sounding speech synthesis with multiple high-quality voices.
- [AWS Polly](https://doc.rapida.ai/integrations/tts/aws-polly.md): Amazon Polly is a cloud-based text-to-speech service that synthesizes natural-sounding speech in dozens of languages and voices.
- [Cartesia Text-to-Speech](https://doc.rapida.ai/integrations/tts/cartesia.md): Cartesia delivers advanced text-to-speech capabilities with ultra-realistic voice synthesis.
- [Resemble AI](https://doc.rapida.ai/integrations/tts/resemble.md): Resemble AI provides high-quality, real-time voice synthesis with support for custom voice cloning.
- [Rime](https://doc.rapida.ai/integrations/tts/rime.md): Rime offers ultra-low-latency text-to-speech with natural-sounding voices via WebSocket streaming.
- [Sarvam AI Text-to-Speech](https://doc.rapida.ai/integrations/tts/sarvam.md): Sarvam AI provides text-to-speech capabilities with strong support for Indian languages.
- [Neuphonic](https://doc.rapida.ai/integrations/tts/neuphonic.md): Neuphonic provides multilingual streaming text-to-speech via WebSocket with adjustable speech speed.
- [MiniMax](https://doc.rapida.ai/integrations/tts/minimax.md): MiniMax provides high-quality speech synthesis via HTTP streaming SSE with multiple model tiers.
- [Groq TTS](https://doc.rapida.ai/integrations/tts/groq.md): Groq provides ultra-fast text-to-speech via an OpenAI-compatible API powered by its LPU inference engine.
- [Speechmatics TTS](https://doc.rapida.ai/integrations/tts/speechmatics.md): Speechmatics provides multilingual HTTP streaming text-to-speech backed by its speech platform.
- [NVIDIA TTS](https://doc.rapida.ai/integrations/tts/nvidia.md): NVIDIA provides enterprise-grade neural text-to-speech via the NVCF API.
- [Custom Text-to-Speech](https://doc.rapida.ai/integrations/tts/custom.md): Configure a custom WebSocket text-to-speech provider with credentials, audio settings, query parameters, request rules, response rules, and the Rapida DSL.
- [Twilio](https://doc.rapida.ai/integrations/telephony/twilio.md): Connect your Twilio phone numbers to Rapida AI for inbound and outbound voice AI conversations.
- [Vonage](https://doc.rapida.ai/integrations/telephony/vonage.md): Connect your Vonage phone numbers to Rapida AI for inbound and outbound voice AI conversations.
- [Exotel](https://doc.rapida.ai/integrations/telephony/exotel.md): Connect your Exotel phone numbers to Rapida AI for inbound and outbound voice AI conversations.
- [Asterisk](https://doc.rapida.ai/integrations/telephony/asterisk.md): Connect your Asterisk PBX to Rapida AI for real-time voice conversations using AudioSocket (native TCP) or WebSocket transport
- [SIP Trunk](https://doc.rapida.ai/integrations/telephony/sip.md): Connect any SIP-compatible PBX, carrier, or VoIP provider to Rapida AI for voice conversations.
- [Rapida Credentials](https://doc.rapida.ai/credential/rapida-credentials.md): Rapida offers two types of credentials: Project Credentials and Personal Tokens, each serving different purposes for authentication and access to Rapida platform services.
- [Workspace Overview](https://doc.rapida.ai/workspace/overview.md): A quick guide to navigating and managing your Rapida workspace
- [Project Management](https://doc.rapida.ai/workspace/project-management.md): Understanding project structure and permissions in the Rapida platform
- [Create a project](https://doc.rapida.ai/workspace/create-new-project.md): Learn how to create a new project in the Rapida platform
- [User Management](https://doc.rapida.ai/workspace/user-management.md): Understanding user roles and management in the Rapida platform
- [Invite a User](https://doc.rapida.ai/workspace/invite-a-user.md): Learn how to invite new users to your Rapida workspace
- [Governance Overview](https://doc.rapida.ai/governances/overview.md): Understand how organizations, projects, users, and roles are structured in the Rapida platform.
- [Organizations](https://doc.rapida.ai/governances/organization.md): Create and manage your organization — the top-level entity that owns all projects, billing, and members in Rapida.
- [Projects](https://doc.rapida.ai/governances/project.md): Projects are isolated workspaces within your organization — each with its own assistants, endpoints, knowledge bases, credentials, and team members.
- [Roles & Permissions](https://doc.rapida.ai/governances/roles-and-permission.md): Your team members access your organization and its projects using individual user accounts which is what you use to sign into RapidaAI. An account must be part of an organization but it does not need to be part of all projects in the organization. Each account will have a single organization role pe…
- [Deployment Options](https://doc.rapida.ai/deployments/deployment-options.md): Understanding how to deploy the Rapida Voice AI Platform
- [Rapida Fully Managed Deployment](https://doc.rapida.ai/deployments/fully-managed.md): Enterprise-managed deployment for teams that need scale without owning the infrastructure
- [Self hosted Deployment](https://doc.rapida.ai/deployments/self-hosted.md): Deploy the Rapida Voice AI Platform on infrastructure your team or clients control
- [Self-Hosting Rapida](https://doc.rapida.ai/opensource/overview.md): Run the full Rapida Voice AI platform on your own infrastructure. Docker Compose gets agencies and enterprise teams to a working deployment quickly while keeping control of data, credentials, and runtime boundaries.
- [Installation](https://doc.rapida.ai/opensource/installation.md): Get Rapida up and running with the deployment model that fits your ownership and scale requirements
- [Architecture Overview](https://doc.rapida.ai/opensource/architecture.md): System architecture, service topology, and data flows for the Rapida Voice AI Platform
- [Configuration Reference](https://doc.rapida.ai/opensource/configuration.md): Complete configuration options for Rapida services
- [Troubleshooting Guide](https://doc.rapida.ai/opensource/troubleshooting.md): Solutions for common Rapida setup and runtime issues
- [Web Console & UI](https://doc.rapida.ai/opensource/services/web-console.md): Web dashboard and user interface for Rapida
- [Web API](https://doc.rapida.ai/opensource/services/web-api/overview.md): Core platform backend. Handles authentication, organization management, credential vault, and acts as the gRPC proxy for all dashboard operations.
- [Web API — Configuration](https://doc.rapida.ai/opensource/services/web-api/configuration.md): Complete environment variable reference for the web-api service.
- [Assistant API](https://doc.rapida.ai/opensource/services/assistant-api/overview.md): Voice orchestration hub. Manages the full real-time pipeline — STT, LLM, TTS — across WebSocket, telephony, and SIP channels.
- [Assistant API — Configuration](https://doc.rapida.ai/opensource/services/assistant-api/configuration.md): Complete environment variable reference for the assistant-api service.
- [Assistant API — Telemetry](https://doc.rapida.ai/opensource/services/assistant-api/telemetry.md): UI setup, runtime wiring, provider options, and telemetry query behavior for assistant-api.
- [Assistant API — Prompt Templating](https://doc.rapida.ai/opensource/services/assistant-api/prompt-templating.md): Prompt argument pipeline, variable namespaces, and rendering behavior in model executor.
- [Local Telephony with ngrok](https://doc.rapida.ai/opensource/services/assistant-api/ngrok.md): Use ngrok to expose assistant-api to Twilio, Vonage, and Exotel webhooks during local development.
- [Telephony — Overview](https://doc.rapida.ai/opensource/services/assistant-api/telephony/overview.md): Provider comparison, URL routing pattern, and inbound call flow for assistant-api telephony.
- [Twilio](https://doc.rapida.ai/opensource/services/assistant-api/telephony/twilio.md): Run assistant-api with Twilio for global PSTN voice calls using WebSocket Media Streams.
- [Vonage](https://doc.rapida.ai/opensource/services/assistant-api/telephony/vonage.md): Run assistant-api with Vonage (Nexmo) for global PSTN voice calls using WebSocket and NCCO.
- [Exotel](https://doc.rapida.ai/opensource/services/assistant-api/telephony/exotel.md): Run assistant-api with Exotel for PSTN voice calls in India and South-East Asia.
- [Asterisk](https://doc.rapida.ai/opensource/services/assistant-api/telephony/asterisk.md): Run assistant-api with Asterisk PBX using AudioSocket (native TCP) or WebSocket transport.
- [SIP](https://doc.rapida.ai/opensource/services/assistant-api/telephony/sip.md): Run assistant-api with the built-in SIP server for direct SIP connectivity.
- [Configure Your Own Telephony Provider](https://doc.rapida.ai/opensource/services/assistant-api/telephony/custom.md): Implement the Telephony and Streamer interfaces to add a new telephony provider to assistant-api.
- [Voice Activity Detection — Overview](https://doc.rapida.ai/opensource/services/assistant-api/vad/overview.md): VAD interface, factory function, providers, and model setup in assistant-api.
- [Silero VAD](https://doc.rapida.ai/opensource/services/assistant-api/vad/silero.md): Configure Silero Voice Activity Detection in assistant-api.
- [TEN VAD](https://doc.rapida.ai/opensource/services/assistant-api/vad/ten.md): Configure TEN Framework Voice Activity Detection in assistant-api.
- [FireRed VAD](https://doc.rapida.ai/opensource/services/assistant-api/vad/firered.md): Configure FireRed Voice Activity Detection in assistant-api.
- [End of Speech Detection — Overview](https://doc.rapida.ai/opensource/services/assistant-api/eos/overview.md): EOS interface, factory function, providers, and model setup in assistant-api.
- [Silence-Based EOS](https://doc.rapida.ai/opensource/services/assistant-api/eos/silence-based.md): Configure silence-based end-of-speech detection in assistant-api.
- [Pipecat Smart Turn EOS](https://doc.rapida.ai/opensource/services/assistant-api/eos/pipecat.md): Configure Pipecat Smart Turn end-of-speech detection in assistant-api.
- [LiveKit Turn Detector EOS](https://doc.rapida.ai/opensource/services/assistant-api/eos/livekit.md): Configure LiveKit Turn Detector end-of-speech detection in assistant-api.
- [Speech-to-Text — Overview](https://doc.rapida.ai/opensource/services/assistant-api/stt/overview.md): STT transformer interface, factory functions, and supported providers in assistant-api.
- [Deepgram STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/deepgram.md): Configure Deepgram Nova-2/Nova-3 speech-to-text in assistant-api.
- [Google Cloud STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/google.md): Configure Google Cloud Speech-to-Text in assistant-api.
- [Azure STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/azure.md): Configure Azure Cognitive Services Speech-to-Text in assistant-api.
- [AssemblyAI STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/assemblyai.md): Configure AssemblyAI real-time speech-to-text with speaker diarization in assistant-api.
- [Rev.ai STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/revai.md): Configure Rev.ai real-time speech-to-text in assistant-api.
- [Sarvam AI STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/sarvamai.md): Configure Sarvam AI speech-to-text for Indian languages in assistant-api.
- [Smallest AI STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/smallest.md): Configure Smallest AI Pulse speech-to-text in assistant-api.
- [Groq STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/groq.md): Configure Groq speech-to-text with ultra-fast Whisper inference in assistant-api.
- [Speechmatics STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/speechmatics.md): Configure Speechmatics real-time speech-to-text with WebSocket streaming in assistant-api.
- [NVIDIA STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/nvidia.md): Configure NVIDIA speech-to-text via the NVCF API in assistant-api.
- [AWS Transcribe STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/aws.md): Configure AWS Transcribe speech-to-text via HTTP in assistant-api.
- [Custom STT](https://doc.rapida.ai/opensource/services/assistant-api/stt/custom.md): Configure a custom WebSocket or HTTP speech-to-text provider in Rapida.
- [Text-to-Speech — Overview](https://doc.rapida.ai/opensource/services/assistant-api/tts/overview.md): TTS transformer interface, factory function, and supported providers in assistant-api.
- [Deepgram Aura TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/deepgram.md): Configure Deepgram Aura text-to-speech in assistant-api.
- [ElevenLabs TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/elevenlabs.md): Configure ElevenLabs text-to-speech with voice cloning in assistant-api.
- [Cartesia TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/cartesia.md): Configure Cartesia ultra-low latency text-to-speech in assistant-api.
- [Google Cloud TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/google.md): Configure Google Cloud Text-to-Speech in assistant-api.
- [Azure TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/azure.md): Configure Azure Cognitive Services Neural text-to-speech in assistant-api.
- [Sarvam AI TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/sarvamai.md): Configure Sarvam AI text-to-speech for Indian languages in assistant-api.
- [Smallest AI TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/smallest.md): Configure Smallest AI Lightning text-to-speech in assistant-api.
- [Rime TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/rime.md): Configure Rime text-to-speech with ultra-low-latency WebSocket streaming in assistant-api.
- [Resemble AI TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/resembleai.md): Configure Resemble AI text-to-speech with real-time WebSocket streaming in assistant-api.
- [Neuphonic TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/neuphonic.md): Configure Neuphonic text-to-speech with WebSocket streaming in assistant-api.
- [MiniMax TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/minimax.md): Configure MiniMax text-to-speech with HTTP streaming SSE in assistant-api.
- [Groq TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/groq.md): Configure Groq text-to-speech with ultra-fast HTTP inference in assistant-api.
- [Speechmatics TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/speechmatics.md): Configure Speechmatics text-to-speech with HTTP streaming in assistant-api.
- [NVIDIA TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/nvidia.md): Configure NVIDIA text-to-speech via the NVCF API in assistant-api.
- [AWS Polly TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/aws.md): Configure AWS Polly text-to-speech via HTTP in assistant-api.
- [Custom TTS](https://doc.rapida.ai/opensource/services/assistant-api/tts/custom.md): Configure a custom WebSocket text-to-speech provider in Rapida.
- [Integration API](https://doc.rapida.ai/opensource/services/integration-api/overview.md): Provider execution layer. Manages encrypted credential storage and executes all external AI provider calls on behalf of assistant-api.
- [Integration API — Configuration](https://doc.rapida.ai/opensource/services/integration-api/configuration.md): Complete environment variable reference for the integration-api service.
- [LLM Providers — Overview](https://doc.rapida.ai/opensource/services/integration-api/llm/overview.md): LargeLanguageCaller interface, ChatCompletionOptions, and supported LLM providers in integration-api.
- [OpenAI](https://doc.rapida.ai/opensource/services/integration-api/llm/openai.md): Configure OpenAI GPT models in integration-api.
- [Anthropic](https://doc.rapida.ai/opensource/services/integration-api/llm/anthropic.md): Configure Anthropic Claude models in integration-api.
- [Google Gemini](https://doc.rapida.ai/opensource/services/integration-api/llm/gemini.md): Configure Google Gemini models in integration-api.
- [Azure OpenAI](https://doc.rapida.ai/opensource/services/integration-api/llm/azure.md): Configure Azure-hosted OpenAI deployments in integration-api.
- [Custom LLM](https://doc.rapida.ai/opensource/services/integration-api/llm/custom.md): Configure a custom LLM endpoint through integration-api.
- [Endpoint API](https://doc.rapida.ai/opensource/services/endpoint-api/overview.md): Webhook and callback management. Routes post-call events to external systems with configurable retry, signature verification, and delivery history.
- [Endpoint API — Configuration](https://doc.rapida.ai/opensource/services/endpoint-api/configuration.md): Complete environment variable reference for the endpoint-api service.
- [Document API](https://doc.rapida.ai/opensource/services/document-api/overview.md): Knowledge base and RAG pipeline. Handles document ingestion, chunking, embedding generation, and semantic search for assistant context retrieval.
- [Document API — Configuration](https://doc.rapida.ai/opensource/services/document-api/configuration.md): config.yaml and environment variable reference for the document-api service.
- [Installation](https://doc.rapida.ai/api-reference/installation.md): Build natural-sounding AI voice assistants with ease
- [Authentication](https://doc.rapida.ai/api-reference/authentication.md): Authentication and connection to use SDK
- [Create Assistant](https://doc.rapida.ai/api-reference/assistant/create-assistant.md): Create an assistant from the Rapida SDK.
- [Create Assistant Provider](https://doc.rapida.ai/api-reference/assistant/create-assistant-provider.md): Create a provider configuration for an existing assistant.
- [Update Assistant Version](https://doc.rapida.ai/api-reference/assistant/update-assistant-version.md): Promote an assistant provider version to the active assistant version.
- [Create Debugger Deployment](https://doc.rapida.ai/api-reference/assistant/create-debugger-deployment.md): Create an assistant debugger deployment from the Rapida SDK.
- [Create API Deployment](https://doc.rapida.ai/api-reference/assistant/create-api-deployment.md): Create an assistant API deployment from the Rapida SDK.
- [Create Web Plugin Deployment](https://doc.rapida.ai/api-reference/assistant/create-webplugin-deployment.md): Create an assistant web plugin deployment from the Rapida SDK.
- [Create Phone Deployment](https://doc.rapida.ai/api-reference/assistant/create-phone-deployment.md): Create an assistant phone deployment from the Rapida SDK.
- [Create WhatsApp Deployment](https://doc.rapida.ai/api-reference/assistant/create-whatsapp-deployment.md): Create an assistant WhatsApp deployment from the Rapida SDK.
- [Get API Deployment](https://doc.rapida.ai/api-reference/assistant/get-api-deployment.md): Get an assistant API deployment from the Rapida SDK.
- [Get Debugger Deployment](https://doc.rapida.ai/api-reference/assistant/get-debugger-deployment.md): Get an assistant debugger deployment from the Rapida SDK.
- [Get Phone Deployment](https://doc.rapida.ai/api-reference/assistant/get-phone-deployment.md): Get an assistant phone deployment from the Rapida SDK.
- [Get Webplugin Deployment](https://doc.rapida.ai/api-reference/assistant/get-webplugin-deployment.md): Get an assistant web plugin deployment from the Rapida SDK.
- [Get WhatsApp Deployment](https://doc.rapida.ai/api-reference/assistant/get-whatsapp-deployment.md): Get an assistant WhatsApp deployment from the Rapida SDK.
- [Get All API Deployments](https://doc.rapida.ai/api-reference/assistant/get-all-api-deployment.md): Get assistant API deployments from the Rapida SDK.
- [Get All Debugger Deployments](https://doc.rapida.ai/api-reference/assistant/get-all-debugger-deployment.md): Get assistant debugger deployments from the Rapida SDK.
- [Get All Phone Deployments](https://doc.rapida.ai/api-reference/assistant/get-all-phone-deployment.md): Get assistant phone deployments from the Rapida SDK.
- [Get All Webplugin Deployments](https://doc.rapida.ai/api-reference/assistant/get-all-webplugin-deployment.md): Get assistant web plugin deployments from the Rapida SDK.
- [Get All WhatsApp Deployments](https://doc.rapida.ai/api-reference/assistant/get-all-whatsapp-deployment.md): Get assistant WhatsApp deployments from the Rapida SDK.
- [Get Assistant](https://doc.rapida.ai/api-reference/assistant/get-assistant.md)
- [Get All Assistants](https://doc.rapida.ai/api-reference/assistant/get-all-assistant.md)
- [Get Assistant Conversation](https://doc.rapida.ai/api-reference/assistant/get-assistant-conversation.md)
- [Get All Assistant Conversations](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-conversation.md)
- [Get Assistant Webhook](https://doc.rapida.ai/api-reference/assistant/get-assistant-webhook.md)
- [Get All Assistant Webhook](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-webhook.md)
- [Get Assistant Knowledge](https://doc.rapida.ai/api-reference/assistant/get-assistant-knowledge.md)
- [Get All Assistant Knowledge](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-knowledge.md)
- [Get Assistant Tool](https://doc.rapida.ai/api-reference/assistant/get-assistant-tool.md)
- [Get All Assistant Tools](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-tool.md)
- [Get Assistant HTTP Log](https://doc.rapida.ai/api-reference/assistant/get-assistant-webhook-log.md)
- [Get All Assistant HTTP Logs](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-webhook-log.md)
- [Get Assistant Analysis](https://doc.rapida.ai/api-reference/assistant/get-assistant-analysis.md)
- [Get All Assistant Analysis](https://doc.rapida.ai/api-reference/assistant/get-all-assistant-analysis.md)
- [Create Phone Call](https://doc.rapida.ai/api-reference/call/create-call.md)
- [Create Bulk Phone Calls](https://doc.rapida.ai/api-reference/call/create-bulk-call.md)
- [Invoke](https://doc.rapida.ai/api-reference/endpoint/invoke.md)
- [Get Endpoint](https://doc.rapida.ai/api-reference/endpoint/get-endpoint.md)
- [Get All Endpoints](https://doc.rapida.ai/api-reference/endpoint/get-all-endpoint.md)
- [Get Endpoint Log](https://doc.rapida.ai/api-reference/endpoint/get-endpoint-log.md)
- [Get All Endpoint Logs](https://doc.rapida.ai/api-reference/endpoint/get-all-endpoint-log.md)
- [Authentication](https://doc.rapida.ai/api-reference/rest/authentication.md): Authenticate REST API requests with an API key.
- [create-assistant](https://doc.rapida.ai/api-reference/rest/assistants/create-assistant.md): Creates an assistant with one provider configuration and optional tools, knowledge, and tags.
- [create-debugger-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/create-debugger-deployment.md): Creates a debugger deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [create-api-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/create-api-deployment.md): Creates an API deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [create-webplugin-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/create-webplugin-deployment.md): Creates a web plugin deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [create-phone-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/create-phone-deployment.md): Creates a phone deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [create-whatsapp-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/create-whatsapp-deployment.md): Creates a WhatsApp deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-api-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-api-deployment.md): Gets the latest API deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-debugger-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-debugger-deployment.md): Gets the latest debugger deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-phone-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-phone-deployment.md): Gets the latest phone deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-webplugin-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-webplugin-deployment.md): Gets the latest web plugin deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-whatsapp-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-whatsapp-deployment.md): Gets the latest WhatsApp deployment for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-all-api-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-all-api-deployment.md): Gets API deployments for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-all-debugger-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-all-debugger-deployment.md): Gets debugger deployments for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-all-phone-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-all-phone-deployment.md): Gets phone deployments for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-all-webplugin-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-all-webplugin-deployment.md): Gets web plugin deployments for an assistant. This endpoint requires user authentication with organization and project scope.
- [get-all-whatsapp-deployment](https://doc.rapida.ai/api-reference/rest/assistant-deployments/get-all-whatsapp-deployment.md): Gets WhatsApp deployments for an assistant. This endpoint requires user authentication with organization and project scope.
- [create-phone-call](https://doc.rapida.ai/api-reference/rest/calls/create-phone-call.md): Starts one outbound phone call using the configured assistant and returns the created conversation identifier.
- [create-bulk-phone-call](https://doc.rapida.ai/api-reference/rest/calls/create-bulk-phone-call.md): Starts multiple outbound phone calls using configured assistants and returns the created conversation identifiers.

## OpenAPI Specs

- [talk-api](https://doc.rapida.ai/openapi/talk-api.yaml)