> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bey.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Monthly release notes for Beyond Presence API, Managed Agents, Studio, and docs.

<Update label="September 2026">
  ## New Features

  * Add self-service avatar creation in Studio ([Custom Avatars](/concepts/avatars/custom))
  * Add multi-factor authentication (MFA) for Studio accounts
  * Add an invoices page in Studio settings with payment details and PDF downloads
  * Add support for `cartesia` agent TTS configs
  * Add new region: asia-south1 (India)

  ## Updates

  * **Avatars:** Faster session startup thanks to avatar prefetching and parallel downloads
  * **Avatars:** Reduced delay before the avatar starts speaking
  * **Agents:** Changed default TTS to Cartesia Sonic 3.6 (from ElevenLabs Flash 2.5)
  * **Agents:** Redesigned the conversation UI, including the pre-join and post-call screens
  * **Agents:** Improved knowledge base handling to support larger files at lower latency
  * **Agents:** Raised the knowledge file text limit from 100,000 to 250,000 characters (both in API and Studio)
  * **Studio:** Redesigned the feedback flow to be less intrusive
  * **API:** Renamed "Call" to "Conversation": `/v1/calls` is now [`/v1/conversations`](/api-reference/agent-conversations/list-conversations)
  * **API:** Renamed `POST /v1/calls` to [`POST /v1/livekit-rooms`](/api-reference/agent-integration/create-livekit-room) ("Create LiveKit Room") in a new "Agent Integration" group. You only need it when embedding a conversation via a LiveKit Client SDK
  * **API:** Old endpoints keep working but now return a `Deprecation` header with a `Link` to their replacement

  ## Bug Fixes

  * Fix agents failing to start when a linked knowledge file was deleted
  * Fix Google TTS for voices other than Chirp 3 HD
  * Fix avatar audio occasionally stalling or skipping very short replies
  * Fix avatar sessions not ending cleanly when the room closes before the agent joins
  * Fix saving custom branding background URLs in Studio
  * Fix incorrect avatar slot calculation; slots now correctly follow your plan ([Concurrency & Quotas](/production/concurrency))
  * Improve Studio sign-in error messages and fix a Google sign-in issue

  ## Documentation

  * Update [Custom Avatars](/concepts/avatars/custom)
  * Add [Knowledge Base](/concepts/agents/knowledge-base) guide
</Update>

<Update label="August 2026">
  ## Breaking Changes

  * Retired Genesis-1 video model: calls, sessions, and videos using a Genesis-1 avatar now return `410 Gone`. All existing Genesis-1 avatars were already silently upgraded to Genesis-2.

  ## Avatars

  * Improve avatar lip sync by giving the model full audio history
  * Improve session stability while avatar models are loading

  ## Managed Agents

  * Changed default OpenAI LLM to GPT 5.4 mini
  * Declare AI interaction in the pre-join screen and in-call UI (following [EU AI Act Art. 50.1](/production/eu-ai-act))
  * Fix room audio occasionally not being attached at the start of a call

  ## Studio

  * Added organizations with user management, role-based access control, and collaboration support
  * Text-to-video generation now includes visible watermarks (following [EU AI Act Art. 50.4](/production/eu-ai-act))

  ## Documentation

  * Redesign docs structure & navbar
  * Redesign onboarding and "Get Started" section: Add [Choose Path](/get-started/choose-path) and quickstarts for [Speech-to-Video](/get-started/quickstart/speech-to-video) and [Managed Agents](/get-started/quickstart/managed-agent)
  * Update [Roadmap](/learn/roadmap)
  * Add [Production Guides](/production) section with [Concurrency & Quotas](/production/concurrency), [GDPR & Privacy](/production/privacy), [EU AI Act](/production/eu-ai-act), [On-Prem Deployment](/production/deployment), and [Troubleshooting](/production/troubleshooting) pages
  * Document [API error codes](/concepts/api/errors)
  * Add page context menu to copy a page or open it in an AI assistant
</Update>

<Update label="July 2026">
  ## New Features

  * Add avatar emotion control for more expressive, natural conversations
  * Support agent creation with [external / custom LLM config](/concepts/agents/external-llm)
  * Support avatar creation via direct file upload

  ## Studio

  * Launch new revamped [Studio experience](https://bey.studio/) with usage analytics, mobile support, and dark theme

  ## Documentation

  * Update API docs
</Update>

<Update label="June 2026">
  ## New Features

  * Add [continuous vision agents](/concepts/agents/extra-capabilities) for real-time perception
  * Improve avatar idle animations
  * Add message-logging control per agent
  * Add billed-minutes usage API

  ## Miscellaneous

  * Add on-prem / enterprise deployment option
</Update>

<Update label="May 2026">
  ## New Features

  * Support [custom avatar backgrounds](/concepts/avatars/custom)
  * Add custom user fields on calls in the developer API

  ## Miscellaneous

  * Improve API endpoint latency
</Update>

<Update label="April 2026">
  ## New Features

  * Add multi-region LLM routing
  * Complete API v2 route parity
</Update>

<Update label="March 2026">
  ## New Features

  * Add more speech-to-text (STT) providers for agents
  * Add [external / custom LLM](/concepts/agents/external-llm) support for agents
  * Add Arabic ([ar-SA](/learn/languages)) language support
  * Add plan-based feature gating

  ## Studio

  * Add video generation support for Genesis-2 avatar videos
</Update>

<Update label="February 2026">
  ## New Features

  * Add Delete Avatar endpoint
  * Support Genesis-2 avatar training from the dashboard
  * Add agent usage tracking
</Update>

<Update label="January 2026">
  ## New Features

  * Add third-party / custom TTS providers
  * Add usage analytics API
  * Improve guardrails

  ## Miscellaneous

  * Add region pinning for data residency
</Update>

<Update label="December 2025">
  ## New Features

  * Add [Knowledge Base files API](/api-reference/agent-knowledge-files/list-knowledge-files)
  * Add session status and start/end timestamps

  ## Miscellaneous

  * Serve downloads and previews via CDN
</Update>

<Update label="November 2025">
  ## New Features

  * Add session concurrency limits
  * Add conversation transcripts via API
  * Add ElevenLabs custom voice support
  * Add [Webhook events](/concepts/agents/webhook-events)

  ## Miscellaneous

  * Add new region: europe-west1
</Update>

<Update label="October 2025">
  ## New Features

  * Add JavaScript support to [LiveKit plugin](/integrations/voice-agents/livekit)
  * Update API reference with [Update Agent endpoint](/api-reference/agents/update-agent)
  * Update speech-to-video with [Pipecat integration](/integrations/voice-agents/pipecat)

  ## Miscellaneous

  * Embed demo as iframe in [Getting Started](/get-started)
  * Update [stock avatars](/concepts/avatars/stock)
</Update>

<Update label="September 2025">
  ## Documentation Revamp

  * Complete documentation restructure and navigation cleanup
  * AI-powered chat integration for instant help
  * Mobile-optimized experience
</Update>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.