May 4, 2026

Conversation tags: Added first-class conversation tags for organizing and filtering conversations. You can now create, update, list and delete tags, assign tags to conversations, and filter conversation history by tag_ids.
Conversation list filters: Added exclude_statuses to list conversations, allowing clients to hide conversations with statuses such as initiated, in-progress, processing, done, or failed.
Model options: Added claude-opus-4-7, gpt-5.4, gpt-5.5, gpt-5.4-2026-03-05, gpt-5.5-2026-04-23, and qwen36-35b-a3b to the LLM enum.
Contextual update metadata: Added contextual_update_info to conversation transcript response items. The field references ContextualUpdateInfo, which includes context_id and is_superseded, so clients can identify contextual updates and whether they have been replaced by later context.
Batch calling filter: Added an optional agent_id query parameter to list workspace batch calling jobs, allowing clients to return jobs for a single agent.
Test invocation listing: Made the agent_id query parameter optional and nullable on list test invocations, allowing clients to list test invocations without filtering by one agent.
MCP response timeout: Increased the maximum response_timeout_secs value from 120 to 300 seconds on MCP server configuration and MCP tool configuration overrides.

Subscription overage: Added current_overage to SubscriptionResponseModel and ExtendedSubscriptionResponseModel.
Resource collections: Added resource_collection to the WorkspaceResourceType enum.

Project image status: Added error and pending_task to ProjectImageResponseModel, and made signed image URLs nullable when an image is still processing or has failed.
Pending media fields: Removed legacy pending_block_ids and pending_external_audio_ids fields from project external audio and video response models.

v2.46.0 - Added keyterms and no_verbatim support to the Scribe realtime API, refactored WebSocket URL construction, and regenerated the SDK for the May 7, 2026 API schema, including conversation tags, conversation list filters, batch calling agent_id filtering, optional test invocation agent_id, contextual update metadata, and MCP response timeout updates.

v2.46.0 - Fern regeneration for the May 7, 2026 API schema, including conversation tags, conversation list filters, batch calling agent_id filtering, optional test invocation agent_id, contextual update metadata, and MCP response timeout updates.

@elevenlabs/client@1.4.0 - Added keyterms (string[]) and noVerbatim (boolean) options to the Scribe realtime API. keyterms are sent as repeated WebSocket query parameters and can include up to 50 terms of up to 20 characters each. noVerbatim removes filler words, false starts, and disfluencies from transcripts. Also fixed a case where interruptions could cut off agent audio that arrived less than 2 seconds after the interruption.
@elevenlabs/types@0.10.0 - Added shared types for Scribe realtime keyterms and noVerbatim.
@elevenlabs/react@1.3.0, @elevenlabs/react-native@1.1.4, @elevenlabs/convai-widget-core@0.11.7, and @elevenlabs/convai-widget-embed@0.11.7 - Updated to the latest client package, including Scribe realtime options and the agent audio interruption fix.
@elevenlabs/react@1.2.2 - Patch release that includes the Scribe realtime options, the agent audio interruption fix, and an automatic random user ID when none is set.

View API changes

New Endpoints

List tags - GET /v1/convai/tags
- Added optional page_size and cursor query parameters
- Returns GetConversationTagsPageResponseModel with conversation_tags, next_cursor, and has_more
Create tag - POST /v1/convai/tags
- Added request body CreateConversationTagRequestModel with required title (string) and optional nullable description (string, max 1000 characters)
- Returns ConversationTagResponseModel
Get tag - GET /v1/convai/tags/{tag_id}
- Returns ConversationTagResponseModel
Update tag - PATCH /v1/convai/tags/{tag_id}
- Added request body PatchConversationTagRequestModel with optional nullable title (string, 1-120 characters) and optional nullable description (string, max 1000 characters)
- Returns ConversationTagResponseModel
Delete tag - DELETE /v1/convai/tags/{tag_id}
Add tag to conversation - POST /v1/convai/conversations/{conversation_id}/tags
- Added request body AssignConversationTagsRequestModel with required tag_ids (array)
Remove tag from conversation - DELETE /v1/convai/conversations/{conversation_id}/tags/{tag_id}

List conversations - GET /v1/convai/conversations
- Added optional nullable exclude_statuses query parameter (array of initiated, in-progress, processing, done, failed)
- Added optional nullable tag_ids query parameter (array of strings)
Get conversation details - GET /v1/convai/conversations/{conversation_id}
- Added tag_ids to GetConversationResponseModel
- Added contextual_update_info to ConversationHistoryTranscriptResponseModel, referencing ContextualUpdateInfo
List workspace batch calling jobs - GET /v1/convai/batch-calling/workspace
- Added optional nullable agent_id query parameter (string)
List test invocations - GET /v1/convai/test-invocations
- Changed agent_id from required string to optional nullable string
MCP server and tool configuration schemas
- Increased response_timeout_secs maximum from 120 to 300 seconds on MCPToolConfigOverride-Input and MCPToolConfigOverride-Output
LLM enum
- Added claude-opus-4-7, gpt-5.4, gpt-5.5, gpt-5.4-2026-03-05, gpt-5.5-2026-04-23, and qwen36-35b-a3b
ConvAIWebhooks
- Added transcript_format
ConversationHistoryMetadataCommonModel
- Added voice_rewards
ConversationChargingCommonModel
- Added asr_usage and tts_usage

SubscriptionResponseModel and ExtendedSubscriptionResponseModel
- Added current_overage
WorkspaceResourceType enum
- Added resource_collection

ProjectImageResponseModel
- Added error and pending_task
ProjectExternalAudioResponseModel and ProjectVideoResponseModel
- Removed pending_block_ids and pending_external_audio_ids