Changelog

March 23, 2026

ElevenAgents

  • Environment Variables API: New environment variables endpoints for managing workspace-level configuration that agents can reference at runtime via {{system_env__<label>}} templating. Supports string, secret, and auth-connection variable types with per-environment value overrides. Endpoints include create, list, get, and update.

  • Auth Connections management: New workspace-level auth connections API for managing authentication credentials used by agent tools and integrations. Supports multiple auth methods including OAuth2 client credentials, JWT, basic auth, bearer tokens, custom headers, and integration-managed OAuth2 authorization code flows. Endpoints include create, list, and delete operations.

  • Knowledge Base URL refresh: New refresh endpoint (POST /v1/convai/knowledge-base/{documentation_id}/refresh) to re-fetch and update content for URL-sourced knowledge base documents. Knowledge base documents also now support auto-sync configuration with enable_auto_sync, auto_remove, and auto_sync_info fields.

  • Guardrail retry with feedback: Custom and content guardrails now support configurable trigger actions with EndCallTriggerAction and RetryTriggerAction options. When set to retry, the agent re-generates its response with injected system feedback up to 3 attempts. Available placeholders include {{trigger_reason}} and {{agent_message}} for contextual retry guidance.

  • Conversation History system variable: Added a new system__conversation_history dynamic variable that provides a lazily-evaluated, JSON-serialized conversation history at runtime. This is useful for passing full conversation context to tools, webhooks, or sub-agent handoffs.

  • Webhook tool content type: Server tools now support a configurable content type for webhook body parameters, allowing you to choose between application/json and application/x-www-form-urlencoded formats. The URL-encoded format is useful for integrating with legacy systems, OAuth token endpoints, and payment processors.

  • WhatsApp outbound messages: Updated the WhatsApp integration with a new outbound message dialog in the dashboard, enabling agents to send outbound messages in addition to calls through the WhatsApp channel.

  • Agent and resource listing filters: The list agents, list knowledge base documents, and list tools endpoints now support a created_by_user_id query parameter (use @me for the current user). The previous show_only_owned_agents and show_only_owned_documents parameters are deprecated.

  • Workflow conditional expressions: Added a new conditional_operator AST node to the workflow expression schema, enabling branching logic within agent workflow definitions.

Music

  • Music Marketplace: New Music Marketplace documentation covering the marketplace for licensing AI-generated music, including usage types, creator payouts, and licensing details.

SDK Releases

Python SDK

  • v2.40.0 - Added environment parameter support for ElevenAgents conversations, enabling environment-specific agent connections. Fern regeneration to match the latest API schema including environment variables, auth connections, knowledge base refresh, and guardrail trigger actions.

JavaScript SDK

  • v2.40.0 - Added multimodal_message WebSocket event type for ElevenAgents real-time conversations. Fern regeneration to match the latest API schema including environment variables, auth connections, knowledge base refresh, and guardrail trigger actions.

iOS SDK

  • v3.1.1 - Added environment parameter support for environment-specific agent connections. Fixed a visionOS build error by bumping the platform requirement to v2.

Packages

Packages v1.0.0 Release Candidate

The first release candidate for v1.0.0 of the ElevenAgents client SDKs is now available. This is a major release with breaking changes that improve the API surface, add granular React hooks for better render performance, and unify the React Native SDK with the React SDK.

To try out the release candidate:

$npm install @elevenlabs/client@next @elevenlabs/react@next @elevenlabs/react-native@next

An elevenlabs:sdk-migration skill is available to help AI coding assistants automatically migrate your codebase to the new APIs. Add it to your Claude Code, Cursor, or Windsurf project to get guided migration support.

Key changes in v1.0.0:

  • @elevenlabs/client: Conversation is now a namespace object and type alias for TextConversation | VoiceConversation instead of a class. The Input and Output classes are replaced by InputController and OutputController interfaces, with new convenience methods on the conversation instance (setMicMuted(), setVolume(), getInputByteFrequencyData(), getOutputByteFrequencyData()). changeInputDevice() and changeOutputDevice() now return void.
  • @elevenlabs/react: useConversation now requires a ConversationProvider ancestor. New granular hooks for fine-grained re-rendering: useConversationControls(), useConversationStatus(), useConversationInput(), useConversationMode(), useConversationFeedback(). New useConversationClientTool() hook for dynamically registering client tools from React components with full type safety.
  • @elevenlabs/react-native: Complete API rewrite replacing ElevenLabsProvider and useConversation with ConversationProvider and the same granular hooks from @elevenlabs/react. WebRTC polyfills and native AudioSession configuration are applied automatically on import.

See the full release notes and migration guides:

API

New Endpoints

ElevenAgents

  • Create environment variable - POST /v1/convai/environment-variables - Create a new environment variable with string, secret, or auth-connection type
  • List environment variables - GET /v1/convai/environment-variables - List all environment variables in the workspace
  • Get environment variable - GET /v1/convai/environment-variables/{env_var_id} - Get a specific environment variable
  • Update environment variable - PATCH /v1/convai/environment-variables/{env_var_id} - Update an environment variable, including per-environment value removal via null
  • Refresh URL document content - POST /v1/convai/knowledge-base/{documentation_id}/refresh - Re-fetch content for URL-sourced knowledge base documents

Workspaces

  • POST /v1/workspace/auth-connections - Create a workspace auth connection with support for OAuth2, JWT, basic, bearer, custom header, and integration-managed auth methods
  • GET /v1/workspace/auth-connections - List all workspace auth connections with dependency information (tools, MCP servers, integration connections)
  • DELETE /v1/workspace/auth-connections/{auth_connection_id} - Delete a workspace auth connection

Speech to Text

  • GET /v1/speech-to-text/evaluation/eval-criteria - List evaluation criteria
  • POST /v1/speech-to-text/evaluation/eval-criteria - Create an evaluation criterion
  • GET /v1/speech-to-text/evaluation/eval-criteria/{criterion_id} - Get a specific evaluation criterion
  • PATCH /v1/speech-to-text/evaluation/eval-criteria/{criterion_id} - Update an evaluation criterion
  • DELETE /v1/speech-to-text/evaluation/eval-criteria/{criterion_id} - Delete an evaluation criterion
  • POST /v1/speech-to-text/evaluation/evaluations - Trigger an evaluation
  • GET /v1/speech-to-text/evaluation/evaluations - List evaluations
  • GET /v1/speech-to-text/evaluation/evaluations/{evaluation_id} - Get a specific evaluation
  • GET /v1/speech-to-text/evaluation/human-agents - List human agents
  • GET /v1/speech-to-text/evaluation/human-agents/{agent_id} - Get a human agent
  • DELETE /v1/speech-to-text/evaluation/human-agents/{agent_id} - Delete a human agent
  • GET /v1/speech-to-text/evaluation/analytics - Get evaluation analytics
  • GET /v1/speech-to-text/evaluation/eval-criteria/{criterion_id}/analytics - Get analytics for a specific criterion
  • GET /v1/speech-to-text/evaluation/human-agents/{agent_id}/analytics - Get analytics for a specific human agent

Updated Endpoints

ElevenAgents

  • Get signed URL, Get conversation token

    • Added environment query parameter (string, optional) for environment-specific resolution

  • List agents

    • Added created_by_user_id query parameter (string, optional, supports @me)
    • Deprecated show_only_owned_agents in favor of created_by_user_id

  • List knowledge base documents

    • Added created_by_user_id query parameter (string, optional, supports @me)
    • Deprecated show_only_owned_documents in favor of created_by_user_id

  • List tools

    • Added created_by_user_id query parameter (string, optional, supports @me)
    • Deprecated show_only_owned_documents in favor of created_by_user_id

  • Get knowledge base chunk

    • Added embedding_model query parameter (string, optional) to specify the embedding model for chunk retrieval

  • Create agent, Update agent, Create draft

    • Added guardrail_trigger_action support with EndCallTriggerAction and RetryTriggerAction schemas
    • Added conditional_operator AST node to workflow expression definitions
    • Agent schemas now support ConvAIEnvVarLocator and EnvironmentAuthConnectionLocator for referencing environment variables in tool configs

  • SIP trunk outbound call

    • Request schema updated to accommodate new environment-related fields

  • Simulate conversation, Simulate conversation stream

    • Added simulation_environment field to request schema

Schema Changes

New Schemas

  • ConvAIEnvironmentVariable, ConvAIEnvironmentVariableCreate, ConvAIEnvironmentVariableUpdate - Environment variable models supporting string, secret, and auth-connection types
  • ConvAIEnvVarLocator, EnvironmentAuthConnectionLocator - Locators for referencing environment variables in tool and MCP server configs
  • EndCallTriggerAction, RetryTriggerAction - Guardrail trigger action schemas for end-call and retry-with-feedback behaviors
  • ConditionalOperator - New AST node for conditional expressions in agent workflows
  • AuthConnectionCreateRequest, AuthConnectionResponse, AuthConnectionDependencies - Workspace auth connection management schemas with support for OAuth2, JWT, basic, bearer, custom header, WhatsApp, and integration-managed auth methods
  • SpeechToTextEvaluation* - Suite of schemas for speech-to-text evaluation criteria, evaluations, human agents, and analytics

Modified Schemas

  • MCPServerConfig, MCPServerConfigOutput - Added support for ConvAIEnvVarLocator references in server configuration
  • CustomGuardrailConfig - Added trigger_action field for configuring end-call or retry behavior
  • Contributor - Added optional bio (string) and profile_id (string) fields
  • ASTLLMNode - Added value_schema field; prompt field is deprecated in favor of value_schema
  • TelephonyDirection - Refactored to a shared enum referenced by multiple conversation and telephony models