August 3, 2026

ElevenAgents

Test-specific tool mocks: Agent simulations and unit tests can now define tool_mock_overrides, keyed by tool ID, to replace shared mocks for one test. ToolResponseMockConfig also adds optional is_error (boolean, default false) so a mock can exercise tool-failure paths.
Translated workflow messages: Literal Say node messages add text_translations, a map of language keys to TranslatedString objects. The field is optional on input and required on output, so strict response validators must accept it.
Conversation version filters: List conversations and Text search conversation messages add the optional version_id query parameter (string) to filter results by agent version.
Knowledge base system tool: Agent configuration adds a knowledge_base system tool with configurable enabled_strategies (SearchStrategy[]). Agent knowledge base RAG queries add optional use_agent_defaults (boolean, default true); set it to false to use neutral retrieval settings while retaining the agent's embedding model.
Agent voice activity detection: Agent create, update, response and workflow-override schemas add vad configuration. VADConfig currently supports background_voice_detection (boolean, default false).
WebSocket custom LLMs: CustomLLMAPIType adds websocket.
File memory controls: Widget file-input configuration adds max_files_in_memory (integer, 1–30, default 10). Files beyond the limit are summarized and released from memory; max_files_per_conversation must be -1 or at least the memory limit.
DTMF input redaction: DTMFInputConfig adds optional redact_input (boolean, default false) to replace caller keypad digits in transcripts, conversation logs and analysis. Digits repeated by the agent or passed to tools remain unchanged.

Speech to Text

Realtime entity detection: Scribe v2 Realtime adds the entity_detection query option. It accepts all, one entity type or category, or an array of types and categories, and emits detected entities in committed_transcript_entities events. See the entity detection guide for supported categories.

Voices

Voice replication across data residencies: Added POST /v1/voices/{voice_id}/replicate-to-isolated-environment for copying an Instant Voice Clone or Voice Design voice to a workspace in the same consolidated billing group. Requests require target_workspace_id (string) and accept preserve_voice_id (boolean, default true); responses return the target voice_id.
Character metadata: Character responses add recommended_voice_ids (string array, default []), metadata adds nullable role (CharacterRole), and CharacterAge replaces middle-aged with middle_aged.

SDK Releases

Packages

@elevenlabs/client@1.16.0, @elevenlabs/react@1.11.0, @elevenlabs/types@0.18.0, @elevenlabs/react-native@1.2.17 and @elevenlabs/convai-widget-core@0.15.0 - Added onAgentReasoningResponsePart, which receives streaming agent reasoning events with start, delta and stop types.
@elevenlabs/convai-widget-core@0.15.0 and @elevenlabs/convai-widget-embed@0.15.0 - Added show_resize_button and the show-resize-button embed attribute. Set either to false to hide the widget header's expand and collapse control.
@elevenlabs/client@1.17.0, @elevenlabs/react@1.12.0, @elevenlabs/types@0.19.0, @elevenlabs/react-native@1.2.18 and @elevenlabs/convai-widget-core@0.15.1 - Added the enableLogging option to Scribe.connect and useScribe. Setting it to false starts an enterprise zero-retention session. The Scribe session_started type now reports enable_logging; the unused disable_logging field was removed.

MCP Server

v0.12.1 - Includes the v0.11 tool updates and a dependency refresh that resolves 44 security alerts.
v0.11.0 - Added simulate_conversation with configurable simulated-user behavior, evaluation criteria, transcript output and pass/fail analysis. The speech_to_text tool now defaults to scribe_v2, and voice_clone now sends audio file contents instead of path strings.

API

View API changes

New Endpoints

Voices

POST /v1/voices/{voice_id}/replicate-to-isolated-environment
- Replicates an Instant Voice Clone or Voice Design voice into another workspace's isolated environment
- Requires target_workspace_id (string)
- Accepts optional preserve_voice_id (boolean, default true)
- Returns required voice_id (string)

Updated Endpoints

ElevenAgents

List conversations - GET /v1/convai/conversations
- Added optional version_id (string) query parameter
Text search conversation messages - GET /v1/convai/conversations/messages/text-search
- Added optional version_id (string) query parameter
POST /v1/convai/agents/{agent_id}/knowledge-base/rag-query
- Added optional use_agent_defaults (boolean, default true) request field

Schema Changes

ElevenAgents

Simulation and unit-test payloads add optional tool_mock_overrides maps; ToolResponseMockConfig adds optional is_error (boolean, default false)
SayNodeLiteralMessage adds text_translations (map of TranslatedString); the field is optional on input and required on output
Agent configuration adds knowledge_base (KnowledgeBaseToolConfig) and vad (VADConfig)
CustomLLMAPIType adds websocket
FileInputConfig adds max_files_in_memory (integer, 1–30, default 10)
DTMFInputConfig adds optional redact_input (boolean, default false)
Realtime agent configuration now defaults to eleven_realtime_v1_mini

Voices

Character responses add recommended_voice_ids (string array, default [])
Character metadata adds nullable role (CharacterRole)
Breaking: CharacterAge replaces middle-aged with middle_aged; clients sending the old value must migrate

Text to Speech

Breaking: removed AudioFilterId and audio_filter from ElevenAgents Text to Speech configuration schemas