# NavTalk API Documentation

## Docs

- [Add Avatar](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-add.md): Create a new avatar training job from a media URL.
- [Get Avatar Cover](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-cover.md): Quickly retrieve an avatar's cover image by avatar ID. Use this endpoint when you only need the cover image and do not want to call the avatar detail endpoint first.
- [Delete Avatar](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-delete.md): Delete an avatar by its ID. If the avatar's training job is still in `Pending` or `Processing` state, the job will also be cancelled automatically.
- [Get Avatar Detail](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-detail.md): Query detailed information of a specific avatar by its ID. Returns complete avatar configuration including provider settings, provider name, model, voice, and prompt information.
- [Get Avatar Detail by Name](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-get-by-name.md): Query detailed information of a specific avatar by its name. Searches both custom avatars (owned by the current license) and system avatars. Returns complete avatar configuration including provider settings, model, voice, prompt information, and provider name.
- [List Avatars](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-list.md): Returns all avatars owned by the current license account.
- [Get Avatar Status](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-status.md): Query the training status of an avatar job. Poll this endpoint after calling `/avatar/add` until the status becomes `Success` or `Failed`.
- [Update Avatar](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-update.md): Update an existing avatar's configuration including name, provider, model, voice, and prompt.
- [Get Avatar Video](https://docs.navtalk.ai/api-reference/endpoint/navtalk/avatar-video.md): Quickly retrieve an avatar's source video by avatar ID. Use this endpoint when you only need the avatar video and do not want to call the avatar detail endpoint first.
- [Upload File](https://docs.navtalk.ai/api-reference/endpoint/navtalk/file-upload.md): Upload an image or video file to the NavTalk storage.
- [Create Model (ElevenLabs)](https://docs.navtalk.ai/api-reference/endpoint/navtalk/model-add.md): Create a new ElevenLabs conversational AI agent (model) with default settings.
- [List Models](https://docs.navtalk.ai/api-reference/endpoint/navtalk/model-list.md): Returns all AI models available under the specified provider. The returned `model` field is used as the `model` parameter when creating an avatar.
- [Issue MQTT Operator Token](https://docs.navtalk.ai/api-reference/endpoint/navtalk/mqtt-operator-token.md): Issue a short-lived MQTT operator token for Transparency Mode.
- [List Providers](https://docs.navtalk.ai/api-reference/endpoint/navtalk/provider-list.md): Returns all AI providers associated with the current license.
- [Create Realtime Chat Connection](https://docs.navtalk.ai/api-reference/endpoint/navtalk/realtime-chat-connection.md): Create a short-lived realtime chat WebSocket connection token and return a ready-to-use `wsUrl`.
- [List Video Compose Tasks](https://docs.navtalk.ai/api-reference/endpoint/navtalk/video-compose-list.md): Returns a paginated list of recent video composition tasks for the current license.
- [Get Video Compose Status](https://docs.navtalk.ai/api-reference/endpoint/navtalk/video-compose-status.md): Query the status and output URLs of a video composition task submitted by the current license.
- [Submit Video Compose Task](https://docs.navtalk.ai/api-reference/endpoint/navtalk/video-compose-submit.md): Submit an asynchronous digital human video composition task.
- [Create Voice](https://docs.navtalk.ai/api-reference/endpoint/navtalk/voice-add.md): Create a new custom voice clone using either ElevenLabs or Cartesia provider.
- [List Voices](https://docs.navtalk.ai/api-reference/endpoint/navtalk/voice-list.md): Returns all voices available under the specified provider. The returned `voice` field is used as the `voice` parameter when creating an avatar.
- [List Voices (Paginated)](https://docs.navtalk.ai/api-reference/endpoint/navtalk/voice-page.md): Returns a page of voices for the specified provider. Unlike `GET /api/open/v1/voice/list`, this endpoint paginates results and does not support filtering by name or gender.
- [Introduction](https://docs.navtalk.ai/api-reference/introduction.md): NavTalk REST API for managing AI providers, models, voices, avatars, and video generation
- [Overview](https://docs.navtalk.ai/api/custom-avatar/overview.md): Learn how to create and train custom digital human avatars for your applications
- [Quick Start](https://docs.navtalk.ai/api/custom-avatar/quick-start.md): Step-by-step guide to creating and training your first custom digital human avatar
- [Reference Materials Requirements](https://docs.navtalk.ai/api/custom-avatar/reference-materials.md): Detailed requirements and best practices for preparing training videos for custom avatar training
- [Introduction](https://docs.navtalk.ai/api/quick-start/introduction.md): Discover NavTalk - Next-generation digital human infrastructure powered by real-time audio processing
- [Camera Recognition](https://docs.navtalk.ai/api/real-time-digital-human-api/camera-recognition.md): Enable real-time camera recognition to let AI analyze and respond to visual input from the user's camera
- [Function Calling](https://docs.navtalk.ai/api/real-time-digital-human-api/function-calling.md): Integrate external APIs and execute custom functions during conversations
- [Maintaining Conversation History](https://docs.navtalk.ai/api/real-time-digital-human-api/historical-dialogue.md): Learn how to maintain conversation history and context across sessions using NavTalk Real-time Digital Human API
- [Knowledge Base Integration](https://docs.navtalk.ai/api/real-time-digital-human-api/knowledge-base-integration.md): Embed your knowledge base directly in the system prompt for accurate, context-aware responses
- [Overview](https://docs.navtalk.ai/api/real-time-digital-human-api/overview.md): Build interactive real-time conversational digital humans with WebSocket-based API
- [Best Practices](https://docs.navtalk.ai/api/real-time-digital-human-api/prompt-engineering/best-practices.md): General techniques for effective prompt engineering with GPT-realtime models
- [Building Effective Prompts](https://docs.navtalk.ai/api/real-time-digital-human-api/prompt-engineering/building-prompts.md): Learn the 10 essential techniques and structure for creating effective GPT-realtime prompts
- [Overview](https://docs.navtalk.ai/api/real-time-digital-human-api/prompt-engineering/overview.md): Learn best practices for building effective system instructions and prompts for GPT-realtime models
- [WebSocket Connection](https://docs.navtalk.ai/api/real-time-digital-human-api/quick-start/establish-connection.md): Learn how to establish WebSocket connections to send user audio input for processing
- [Get API Key](https://docs.navtalk.ai/api/real-time-digital-human-api/quick-start/get-api-key.md): Register for an account and obtain your API key to start using NavTalk Real-time Digital Human API
- [WebRTC Connection](https://docs.navtalk.ai/api/real-time-digital-human-api/quick-start/webrtc-connection.md): Learn how to establish WebRTC connections to receive audio and video responses from the NavTalk Real-time Digital Human API
- [Supported Languages](https://docs.navtalk.ai/api/real-time-digital-human-api/supported-languages.md): Complete list of languages supported by NavTalk Real-time Digital Human API
- [Transparency Mode](https://docs.navtalk.ai/api/real-time-digital-human-api/transparency-mode.md): Use the Real-time Digital Human API in transparency mode and connect your own reply pipeline through MQTT.
- [Business Consultant](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/business-consultant.md): Use Lisa as a business consultant to provide strategic business advice and professional guidance
- [Educational Tutor](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/educational-tutor.md): Use Gabriela as an educational tutor to provide personalized lessons adapted to learning style
- [Fitness Trainer & Tech Support](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/fitness-tech-support.md): Use Owen to provide fitness coaching and technical support expertise
- [Research Assistant](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/research-assistant.md): Use Lily as a research assistant for information gathering and research analysis
- [Sales Coach](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/sales-coach.md): Use Luke as a sales coach to provide scalable one-on-one sales training and guidance
- [Virtual Interviewer](https://docs.navtalk.ai/api/real-time-digital-human-api/use-cases/virtual-interviewer.md): Use Lauren as a virtual interviewer to conduct engaging candidate screening at scale
- [Supported Voice Styles](https://docs.navtalk.ai/api/real-time-digital-human-api/voice-styles.md): Browse all available voice styles for Real-time Digital Human API
- [conversation.connected.close](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/connection-events/conversation-connected-close.md): WebSocket connection closed event
- [conversation.connected.fail](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/connection-events/conversation-connected-fail.md): WebSocket connection failed event
- [conversation.connected.success](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/connection-events/conversation-connected-success.md): WebSocket connection successful event
- [conversation.connected.warning](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/connection-events/conversation-warning.md): Connection warning event for non-critical issues (e.g., duplicate avatar names)
- [conversation.connected.backend_error](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/error-events/session-backend-error.md): Backend error event
- [conversation.connected.connection_limit_exceeded](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/error-events/session-connection-limit-exceeded.md): Maximum concurrent connections exceeded error
- [conversation.connected.gpu_full](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/error-events/session-gpu-full.md): GPU resources exhausted error
- [conversation.connected.insufficient_balance](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/error-events/session-insufficient-balance.md): Insufficient account balance error
- [realtime.response.function_call_arguments.done](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/function-call-events/response-function-call-arguments-done.md): Function call request event
- [realtime.conversation.item.input_audio_transcription.completed](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/input-events/conversation-item-input-audio-transcription-completed.md): User speech transcription completed event
- [realtime.input_audio_buffer.speech_started](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/input-events/input-audio-buffer-speech-started.md): User started speaking event
- [realtime.input_audio_buffer.speech_stopped](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/input-events/input-audio-buffer-speech-stopped.md): User stopped speaking event
- [realtime.input_image](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/input-events/input-image.md): Send camera image to AI for visual recognition and analysis
- [Overview](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/overview.md): Overview of all WebSocket message events in real-time digital human conversations
- [realtime.response.audio.delta](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/response-events/response-audio-delta.md): Streaming audio chunks (optional)
- [realtime.response.audio.done](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/response-events/response-audio-done.md): Audio generation completed
- [realtime.response.audio_transcript.delta](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/response-events/response-audio-transcript-delta.md): Streaming text chunks as AI generates response
- [realtime.response.audio_transcript.done](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/response-events/response-audio-transcript-done.md): Complete text response finished
- [realtime.session.created](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/session-events/session-created.md): Session created event
- [realtime.session.updated](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/session-events/session-updated.md): Session ready event
- [webrtc.signaling.answer](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/webrtc-events/webrtc-signaling-answer.md): WebRTC answer signaling event
- [webrtc.signaling.iceCandidate](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/webrtc-events/webrtc-signaling-icecandidate.md): WebRTC ICE candidate signaling event
- [webrtc.signaling.offer](https://docs.navtalk.ai/api/real-time-digital-human-api/websocket-events/webrtc-events/webrtc-signaling-offer.md): WebRTC offer signaling event
- [Available Avatars](https://docs.navtalk.ai/api/resources/avatars.md): Browse all available built-in avatar characters for your digital human
- [Conversations](https://docs.navtalk.ai/api/resources/conversations.md): Reference for querying conversation sessions and message history programmatically
- [FAQ](https://docs.navtalk.ai/api/resources/frequently-asked-questions.md): Common questions and answers about NavTalk API
- [Changelog](https://docs.navtalk.ai/api/resources/update-log.md): Record of important updates including features, API changes, and optimizations
- [Webhook](https://docs.navtalk.ai/api/resources/webhook.md): Integration guide for receiving real-time conversation events and complete session records via Webhook
- [API Reference](https://docs.navtalk.ai/api/video-synthesis-api/editor.md): Reference for the open Video Synthesis API submit, status, and list endpoints
- [Overview](https://docs.navtalk.ai/api/video-synthesis-api/overview.md): Generate digital human videos with the open Video Synthesis API using avatar IDs, uploaded files, or external media URLs
- [Quick Start](https://docs.navtalk.ai/api/video-synthesis-api/quick-start.md): Submit your first video composition task with the open Video Synthesis API
- [Avatar Voice and TTS Providers](https://docs.navtalk.ai/api/video-synthesis-api/voice-styles.md): Understand how avatar-bound voices and TTS providers work in the open Video Synthesis API

## OpenAPI Specs

- [openapi](https://docs.navtalk.ai/api-reference/openapi.json)