Changelog

ElevenAgents, ElevenCreative and ElevenAPI

We’re moving from a single-product perception (“ElevenLabs”) to a platform-based structure with clearly defined product families:

• ElevenAgents (Formerly Agents Platform)
• ElevenCreative (Formerly Creative Platform)
• ElevenAPI (New, the Developer Platform)

You’ll already see this reflected in the docs and SDK readmes.

Global servers out of beta

Global routing is now the default rather than opt-in.

Previously the default ElevenLabs API server was located in the United States, with an opt-in beta for routing traffic through the Netherlands or Singapore based servers. As of now global routing is the default, meaning that the server will automatically be chosen based on geographic proximity to optimize latency.

The opt-in base URL api-global-preview.elevenlabs.io is now deprecated, please use the default api.elevenlabs.io base URL instead. If you’re using the SDKs, this is already the default.

Text to Speech

• TTS Normalizer v3.1: Upgraded the text normalizer to version 3.1, which includes improved accuracy and lower latency for text-to-speech conversion.

Agents Platform

• Custom guardrails: Added support for user-defined output guardrails that allow you to create custom content filtering rules beyond standard moderation. Configure guardrails with a name, prompt instruction (up to 10,000 characters), and choice of evaluation model (gemini-2.5-flash-lite or gemini-2.0-flash). When triggered, the guardrail ends the conversation. See the Security documentation for details.
• WhatsApp outbound messaging: Added Send outbound message endpoint (POST /v1/convai/whatsapp/outbound-message) to initiate conversations via WhatsApp using message templates. Required fields include whatsapp_phone_number_id, whatsapp_user_id, template_name, template_language_code, template_params, and agent_id.
• Eleven v3 conversational model: Added eleven_v3_conversational to the available TTS models for agents, providing improved voice quality and expressiveness in agent conversations.
• Suggested audio tags: Added suggested_audio_tags field to TTS configuration for agents using v3 models. Define up to 20 tags (e.g., “happy”, “excited”) to guide expressive speech generation, with optional descriptions for when each tag should be used.
• Tool error handling: Added tool_error_handling_mode field to webhook tool configurations with options: auto (default, determines handling based on tool type), summarized (sends LLM-generated summary), passthrough (sends raw error), or hide (does not share error with agent).
• Dynamic variable sanitization: Added sanitize field (boolean, default false) to DynamicVariableAssignment. When enabled, the assignment value is removed from tool responses and transcripts while still being processed for variable assignment.
• Turn model selection: Added TurnModel enum with turn_v2 and turn_v3 options for selecting the turn detection model version.
• Workflow node transfers: Added is_workflow_node_transfer field (boolean, default false) to AgentTransfer schema for identifying transfers within workflow nodes.
• Transfer branch metadata: Added TransferBranchInfoTrafficSplit and TransferBranchInfoDefaultingToMain schemas for tracking branch routing information in agent transfers.
• Workflow node transition testing: Added workflow_node_transition assertion type for unit tests with UnitTestWorkflowNodeTransitionEvaluationNodeId schema to validate agent workflow transitions.

Studio

• Muted tracks endpoint: Added Get project muted tracks endpoint (GET /v1/studio/projects/{project_id}/muted-tracks) that returns a list of chapter IDs with muted tracks in a project.

Workspaces

• Lite member seat type: Added workspace_lite_member to the SeatType enum for workspaces with limited access permissions.
• Content templates resource: Added content_templates to WorkspaceResourceType enum for sharing content templates within workspaces.

User Interface

• Voice collection scrolling: Fixed an issue preventing mouse wheel and touch scrolling in the voice collection icon picker on macOS.

SDK Releases

Python SDK

• v2.35.0 - Added custom guardrails, WhatsApp outbound messaging, tool error handling mode, dynamic variable sanitization, turn model selection, and Eleven v3 conversational model support

JavaScript SDK

• v2.35.0 - Added custom guardrails, WhatsApp outbound messaging, tool error handling mode, dynamic variable sanitization, turn model selection, and Eleven v3 conversational model support

React and Client SDKs

• @elevenlabs/react-native@0.5.10 - Fixed establishing text-only conversations
• @elevenlabs/react@0.14.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations
• @elevenlabs/client@0.14.0 - Reduced audio chunk length from 250ms to 100ms for lower latency, normalized textOnly option handling between top-level and overrides object
• @elevenlabs/types@0.5.0 - Added types for audio alignment data support

API