agent_response_complete WebSocket event: A new agent_response_complete client event fires exactly once when an agent’s response is fully delivered — after all LLM generation, tool call chains, and audio playback complete. After this event, the agent will only produce further output if the user provides new input or a turn timeout triggers a new turn. The event lets clients reliably detect end of turn for batching messages, wake-word activation, or post-turn UI updates. Added a new AGENT_RESPONSE_COMPLETE value to the ClientEvent enum and a corresponding AgentResponseCompleteClientEvent response model.
Pre-tool speech mode: Added a new pre_tool_speech field (PreToolSpeechMode enum, default auto) on MCP server configuration and per-tool overrides. Replaces the now-deprecated force_pre_tool_speech boolean. Values: auto decides whether the agent speaks before the tool call based on recent tool latency, force always asks the agent to speak, and off opts out entirely.
Tool dispatch respects execution mode: Workflow tool dispatch nodes now correctly respect each nested tool’s execution_mode. If any tool in a dispatch node uses POST_TOOL_SPEECH, the workflow waits for the current turn’s audio to be fully exposed before executing the dispatch.
MCP response timeout: Added a response_timeout_secs field (integer, default 30, min 5, max 120) on MCP server configuration and per-tool overrides, controlling the maximum time to wait for each MCP tool call to complete.
Agent trust context: Added a trust_context field on agent platform settings (AgentTrustContext enum: unknown | low | high, default unknown). low is for agents serving untrusted external participants, where outputs should be vetted and tool access scoped; high is for agents serving the owner where full tool access is appropriate; unknown covers agents created before this feature.
Source attribution toggle: Added a source_attribution boolean (default false) on conversation config. When enabled and knowledge base content is present, the LLM is instructed to report which sources it used.
Test sharing mode filter: The list tests endpoint now accepts a sharing_mode query parameter (all | shared_with_me, default all) to filter tests and folders to only those shared with the current user that they did not create.
Tool icons and execution metadata: Added icons (array of Icon) and execution (ToolExecution) fields to the Tool schema. Icon includes src, mimeType, and sizes for UI display, and ToolExecution.taskSupport (forbidden | optional | required) declares how the tool participates in tasks.
Procedure compiler default: The ProcedureCompilerMode default has changed from deterministic to append, and the llm value has been removed. Existing agents that explicitly set deterministic are unaffected.
RAG and knowledge base attribution metadata: Added used_static_kb_document_ids (array of strings) on ConversationHistoryTranscriptCommonModel and ConversationHistoryTranscriptResponseModel, and used_chunk_ids on RagRetrievalInfo, surfacing exactly which knowledge base documents and RAG chunks contributed to each transcript turn.
Dynamic variable refactor: dynamic_variables and dynamic_variable_placeholders now reference unified DynamicVariableValueType-Input / DynamicVariableValueType-Output schemas (replacing the prior DynamicVariableContainerValueType-* schemas), with broader support for nested and list values. DynamicVariableAssignment gained a preserve_native_type field to keep typed values rather than coercing to strings.
GET /v1/audio-isolation/history) returns a paginated list of all your audio isolation generations. Supports page_size, page, and search query parameters.DELETE /v1/audio-isolation/history/{history_item_id}) deletes a specific item and its associated media files.keyterms parameter (array of strings, max 50 entries of up to 20 characters each) to bias the model toward specific terms, and a no_verbatim boolean to remove filler words, false starts, and disfluencies from transcripts. Both parameters are echoed back in the session_started event. Available across the JavaScript SDK, Python SDK, and the @elevenlabs/client browser/Node client SDK.pre_tool_speech and response_timeout_secs, and the agent_response_complete client event. Also includes a fix to the notebook install hint in the README.trust_context field, pre_tool_speech mode, asset transcription support, and MCP response timeout configuration.keyterms (string array, max 50 keyterms of up to 20 chars each) and noVerbatim (boolean) options on the Scribe realtime client. keyterms are sent as repeated query parameters on the WebSocket URL to bias transcription, and noVerbatim removes filler words and disfluencies. Both fields are also added to the typed Config interface for the session_started echo. Also includes the April 27, 2026 Fern regeneration (#376).trust_context field, pre_tool_speech mode, and MCP response timeout configuration.end_call tool). onAgentDisconnected now disconnects the LiveKit room and tears down conversation state, with onDisconnect firing an .agent reason. ConnectionManaging.onAgentDisconnected is now async. Removed the unused ConversationConnectionManager wrapper.@elevenlabs/client@1.3.1 / @elevenlabs/client@1.3.0, picking up the tool-call sound fix and conversation file upload support.@elevenlabs/client for the same fixes.@elevenlabs/client@1.3.1 for the tool-call sound fix.@elevenlabs/client@1.3.0 for conversation file upload support.GET /v1/audio-isolation/historyDELETE /v1/audio-isolation/history/{history_item_id}GET /v1/convai/tools/{tool_id}/executions returns paginated tool executions for a specific tool with optional cursor, page_size, is_error, agent_id, branch_id, start_time, and end_time filtersCreate agent, Get agent, Update agent
trust_context field (AgentTrustContext enum: unknown | low | high, default unknown) on AgentPlatformSettingsRequestModelsource_attribution field (boolean, default false) on ConversationConfigUpdate MCP server configuration, Create MCP server
pre_tool_speech field (PreToolSpeechMode enum: auto | force | off, default auto)response_timeout_secs field (integer, default 30, min 5, max 120)Create configuration override, Update configuration override
pre_tool_speech field (PreToolSpeechMode enum, nullable, optional)response_timeout_secs field (integer, nullable, optional)response_mocks field on MCPToolConfigOverride-Input / MCPToolConfigOverride-Outputforce_pre_tool_speech as deprecated; use pre_tool_speech insteadsharing_mode query parameter (TestSharingMode enum: all | shared_with_me, default all)Simulate conversation, Stream simulate conversation
dynamic_variables and dynamic_variable_placeholders payloads to reference unified DynamicVariableValueType-Input / DynamicVariableValueType-Output schemas with broader nested and list value supportTool schema
icons field (array of Icon, nullable) for UI displayexecution field (ToolExecution, nullable) including taskSupport (forbidden | optional | required)ClientEvent enum
agent_response_complete value with new AgentResponseCompleteClientEvent response modelProcedureCompilerMode enum
deterministic to appendllm valueConversationHistoryTranscriptCommonModel, ConversationHistoryTranscriptResponseModel
used_static_kb_document_ids field (array of strings)RagRetrievalInfo
used_chunk_ids field (array of strings)DynamicVariableAssignment
preserve_native_type field (boolean) for keeping typed values instead of coercing to stringsWorkflow nodes
auto_advance_after_first_response field on relevant workflow node schemasTool configuration documentation
response_body_schema field for documenting expected response shapeGetUserSubscriptionResponseModel
max_credit_limit_extension fieldGet workspace usage by product over time
start_time and end_time minimums raised to 2020-01-01, with descriptions added on both fields. The endpoint summary was renamed to Get Workspace Usage.Currency enum with values eur, inr, usd, replacing inline currency strings in several schemas.AssetTranscription and AssetTranscriptionData schemas extend asset models with transcription support.PendingBlocksMetadataModel and PendingExternalAudiosMetadataModel provide richer metadata on pending tasks.InVPC value added to source-related enums.keyterms now have explicit length restrictions in the spec.MemoryEntrySearchResult, ConversationSource, and ManualSource schemas added.