Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.bithuman.ai/llms.txt

Use this file to discover all available pages before exploring further.

This page tracks product-level changes (platform, web, agent runtime). For per-version release notes of the bithuman PyPI package specifically, see the Python SDK CHANGELOG. For the Swift SDK (bitHumanKit), see the bithuman-kit-public Releases page.

​
April 2026

​
Chat Widget v5

  • New bithuman-chat-widget-v5.js with text, voice, and video modes in a single floating widget
  • Configurable themes (light/dark), accent colors, FAB styles (bar/circle)
  • Public API: BitHumanChat.open(), close(), isOpen(), setTheme(), destroy()
  • Suggested questions and custom welcome message support

​
FAQ Knowledge Base Improvements

  • FAQ search now always executes (no early exit on keyword match)
  • Removed duplicate FAQ deduplication logic that was dropping valid results

​
Voice Mode Enhancements

  • Siri-style animation during voice interactions
  • Multilingual TTS support: 11 new languages with automatic voice selection
  • Thai, Chinese, Arabic, and additional language support

​
Streaming & Performance

  • Instant text streaming to the UI without waiting for audio sync

​
March 2026

​
Platform UI Refresh

  • Redesigned navigation: sidebar with Explore, Library, Billing, Developer sections
  • Explore replaces the old Community page — browse agents, apps, videos, and books with category filters
  • Library replaces My Agents — view and manage your agents with new side-panel settings (Identity, Features, Distribute, Developer tabs)
  • Developer section consolidates API Keys, Webhooks, Integrations, and Docs in one place
  • New top navigation: Platform, Create, Plan, Docs, Case Studies, Contact
  • Credit balance visible in the top navigation bar
  • Agent context menu: Launch Agent, Create Video, Share, Clone, Embed, Download

​
Documentation Updates

  • Updated all screenshots to match the March 2026 UI
  • Updated all navigation references (Developer → API Keys, Explore page, Library)
  • Updated prerequisites snippet with new Explore page download flow

​
February 2026

​
Expression Avatar v2

  • 24% faster rendering pipeline with optimized video decoder
  • Eliminates visual artifacts in concurrent sessions

​
Self-Hosted GPU Container

  • Published Expression Avatar Docker image for self-hosted deployment
  • Supports up to 8 concurrent sessions per GPU
  • Cold start ~50s, warm start 4-6s
  • ~5 GB auto-downloaded model weights (cached in Docker volume)

​
Developer Examples Overhaul

  • Fixed Docker Compose env_file handling across all 4 example stacks
  • Standardized .env.example files with section headers and inline help
  • Expanded READMEs with architecture diagrams, config tables, verification steps
  • Added api/test.py for zero-friction API credential validation
  • Added AGENTS.md for AI coding agent discoverability
  • Added llms.txt and llms-full.txt for AI documentation indexing
  • Published OpenAPI specification

​
REST API

  • POST /v1/agent/{code}/speak — make avatar speak text in active sessions
  • POST /v1/agent/{code}/add-context — inject silent background knowledge
  • Improved error responses with consistent error codes and messages

​
SDK & Plugin

  • livekit-plugins-bithuman — Expression model support with model="expression"
  • bithuman.AvatarSession — unified interface for cloud, CPU, and GPU modes
  • Animal mode support for Essence avatars

​
January 2026

​
Essence Avatar

  • CPU-only avatar rendering from .imx model files
  • 25 FPS real-time on 4+ core machines
  • Cross-platform: Linux, macOS (M2+), Windows (WSL)

​
Platform API

  • Agent generation from text prompts + image/video/audio
  • Agent management (CRUD operations)
  • File upload (URL and base64)
  • Dynamics/gesture generation and triggering

​
Integrations

  • LiveKit Cloud Plugin
  • Website embed (iframe with JWT)
  • Webhooks (room.join, chat.push events)
  • Flutter full-stack example
For feature requests and bug reports, visit our GitHub or Discord.