Build real-time conversational video agents — AI-powered avatars that see, hear, speak, and reason with users in under 1 second of latency.
| --- | --- |
| API Base URL | https://api.trugen.ai |
| Authentication | x-api-key: header on all requests |
| Official Docs | docs.trugen.ai |
| Developer Portal | app.trugen.ai |
| Variable | Description | Where to Get |
|---|---|---|
| ---------- | ------------- | -------------- |
TRUGEN_API_KEY | Primary API key for all Trugen API calls (sent as x-api-key header) | Developer Portal |
TRUGEN_AVATAR_ID | (Optional) Default avatar ID for LiveKit integration | Developer Portal |
> Security: Never expose TRUGEN_API_KEY in client-side code. For widget/iFrame embeds, use a server-side proxy to keep keys secret. See references/embedding.md for details.
| Step | Component | Function |
|---|---|---|
| ------ | ----------- | ---------- |
| 1 | WebRTC | Bidirectional audio/video streaming |
| 2 | STT (Deepgram) | Streaming speech-to-text |
| 3 | Turn Detection | Natural conversation boundary detection |
| 4 | LLM (OpenAI, Groq, custom) | Contextual response generation |
| 5 | Knowledge Base | Grounding answers in your data |
| 6 | TTS (ElevenLabs) | Natural, expressive speech synthesis |
| 7 | Huma-01 | Neural avatar video generation with lip sync & microexpressions |
POST /v1/ext/agent — see references/agents.md| Resource | Endpoints | Reference |
|---|---|---|
| ---------- | ----------- | ----------- |
| Agents | Create, Get, List, Update, Delete, Create from Template | agents.md |
| Knowledge Base | Create KB, Add Docs, Get, List, Update, Delete KB/Doc | knowledge-base.md |
| Templates | Create, Get, List, Update, Delete persona templates | templates.md |
| Tools & MCPs | Create/manage function-calling tools and MCP servers | tools-and-mcps.md |
| Webhooks | Callback events, payload format, handler examples | webhooks.md |
| Embedding | iFrame, Widget, LiveKit integration + avatar IDs | embedding.md |
| Providers/Avatars | Available LLMs, STT, TTS, avatars, languages, BYO-LLM | providers-avatars-languages.md |
| Prompting | Voice prompt strategies, guardrails, use case examples | prompting-and-use-cases.md |
Retrieve transcripts for completed sessions:
GET /v1/ext/conversation/{id} — Returns agent_id, status, transcript array, recording_url.
Determine what the user needs, then load the appropriate reference:
| Task | Reference File |
|---|---|
| ------ | --------------- |
| Creating/managing agents | agents.md |
| Attaching data/documents | knowledge-base.md |
| Reusing personas across agents | templates.md |
| Calling external APIs from agent | tools-and-mcps.md |
| Reacting to conversation events | webhooks.md |
| Embedding agent in website | embedding.md |
| Choosing LLM/voice/language | providers-avatars-languages.md |
| Writing effective prompts | prompting-and-use-cases.md |
| Resource | Link |
|---|---|
| ---------- | ------ |
| Documentation | docs.trugen.ai |
| API Reference | docs.trugen.ai/api-reference |
| Developer Portal | app.trugen.ai |
| Community Discord | discord.gg/4dqc8A66FJ |
| Support | support@trugen.ai |
| GitHub Examples | trugenai/trugen-examples |
| Changelog | docs.trugen.ai/changelog |
共 1 个版本