Changelog

February 23, 2026

February 23, 2026

ElevenAgents

  • OAuth and advanced authentication for MCP servers: MCP servers now support workspace auth connections, enabling OAuth2 Client Credentials, Basic Auth, Bearer Auth, JWT, and custom header authentication. Select an auth connection when creating or editing an MCP server to automatically handle token refresh and authentication headers. See the MCP server documentation for more details.
  • LLM information endpoint: Added a new endpoint to list available LLMs with deprecation status, capabilities, and context limits. This enables clients to programmatically discover which models are available and which are being deprecated. See List Available LLMs for details.
  • Conversation history redaction: Added support for redacting sensitive information from conversation transcripts, audio, and analysis before being stored. Configure specific entity types to redact (such as names, email addresses, etc.) using the new conversation_history_redaction setting in agent privacy configuration. See the docs page for more details.
  • Enhanced guardrails: Introduced two new guardrail types for agents:
    • focus: Helps keep conversations on-topic
    • prompt_injection: Detects and prevents prompt injection attempts
    • Note: The alignment guardrail has been removed
  • Conversation search endpoints: Added two new endpoints for searching conversation messages:
    • Text search - Full-text and fuzzy search over transcript messages
    • Smart search - Semantic search using embeddings
  • File uploads in conversations: Added endpoints to upload and manage files within conversations:
  • New embedding model: Added support for qwen3_embedding_4b embedding model in knowledge base RAG indexing.

Workspaces

  • Image and video generation permission: Workspace administrators can now control access to image and video generation features. This new permission allows you to restrict which workspace members can use these capabilities. Configure this in your workspace settings under member permissions.

Music

  • Workspace sharing: Songs can now be shared within workspaces. The songs resource type has been added to workspace resource sharing endpoints.

SDK Releases

JavaScript SDK

  • v2.36.0 - Added overloaded convert method signatures to Speech to Text wrapper for improved type safety and ergonomics. Updated SDK to include latest API schema changes including LLM list endpoint, conversation search, and MCP auth connection support.

Python SDK

  • v2.36.1 - Added missing music generation parameters including seed, loudness, quality, and guidance_scale to ensure full feature parity with the API.
  • v2.36.0 - Renamed package references from “Conversational AI” to “ElevenAgents” to reflect the product rebrand. Updated SDK to include latest API schema changes including LLM list endpoint, conversation search, and MCP auth connection support.

Packages

API

New Endpoints

  • Text search conversation messages - GET /v1/convai/conversations/messages/text-search - Perform full-text or fuzzy search over conversation transcript messages
  • Smart search conversation messages - GET /v1/convai/conversations/messages/smart-search - Perform semantic search over conversation messages using embeddings
  • List available LLMs - GET /v1/convai/llm/list - Retrieve available LLMs with deprecation information, capabilities, and context limits
  • Upload file to conversation - POST /v1/convai/conversations/{conversation_id}/files - Upload files to a conversation context
  • Delete conversation file - DELETE /v1/convai/conversations/{conversation_id}/files/{file_id} - Remove an uploaded file from a conversation

Removed Endpoints

The following legacy voice generation endpoints have been removed:

  • GET /v1/voice-generation/generate-voice/parameters - Voice Generation Parameters
  • POST /v1/voice-generation/generate-voice - Generate A Random Voice
  • POST /v1/voice-generation/create-voice - Create A Previously Generated Voice

Use the Voice Design and Voice Remix endpoints instead.

Updated Endpoints

ElevenAgents

  • Create agent, Update agent, Get agent

    • Added coaching_settings field for agent training configuration
    • Added conversation_history_redaction in platform_settings.privacy with configurable entity types
    • Added new guardrails: focus and prompt_injection in platform_settings.guardrails
    • Removed alignment guardrail from platform_settings.guardrails
    • Added qwen3_embedding_4b as an embedding model option in RAG configuration
    • Updated numeric field descriptions for better clarity on ranges and defaults

  • Create MCP server, Update MCP server, Get MCP server

    • Added auth_connection field (optional) to enable OAuth and advanced authentication methods
    • Added secret_token field to PATCH endpoint for backward compatibility
    • Auth connection takes precedence over secret_token when both are provided

  • Create MCP tool config, Update MCP tool config, Get MCP tool config

    • Added input_overrides field - allows overriding tool input parameters with constants, dynamic variables, or LLM-generated values

  • Create RAG index, Delete RAG index

    • Added qwen3_embedding_4b to the embedding_model enum

  • Get conversations

    • Deprecated search query parameter (use the new dedicated search endpoints instead)

  • Get conversation

    • Added hiding_reason field to indicate why a conversation might be hidden
    • Extended conversation transcript entries to support file_input metadata with new ChatSourceMedium type (audio, text, image, file)

  • Simulate conversation, Simulate conversation stream

    • Updated all nested configuration fields with improved descriptions and validation ranges

  • Get agent branches, Update agent branch

    • Updated current_live_percentage field description for clarity

  • Get ElevenAgents settings, Update ElevenAgents settings

    • Updated rag_retention_period_days field with improved description

Workspaces

Music

  • Generate music, Generate music detailed, Stream music
    • Clarified seed parameter description: Random seed for music generation initialization. Providing the same seed with identical parameters helps achieve more consistent results, but exact reproducibility is not guaranteed and outputs may change across system updates. Cannot be used with prompt parameter.

Text to Voice

  • Create voice previews, Design voice, Remix voice
    • Updated loudness parameter description: Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS
    • Updated guidance_scale parameter description: Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. Longer, more detailed prompts work better at lower guidance scale.
    • Updated quality parameter description for voice preview creation

Voices

  • Get voices, Get voice settings, Get default voice settings, Edit voice settings
    • Updated style parameter description: Determines the style exaggeration of the voice. Attempts to amplify the style of the original speaker. Consumes additional computational resources and might increase latency if set to anything other than 0
    • Updated speed parameter description: Adjusts the speed of the voice. 1.0 is default, values less than 1.0 slow down speech, values greater than 1.0 speed it up