For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Exotel telephony integration: Added Exotel as a first-class telephony provider alongside Twilio and SIP trunking. New Exotel outbound call endpoint (POST /v1/convai/exotel/outbound-call) initiates outbound calls via the Exotel Connect API with agent_id, agent_phone_number_id, to_number, optional conversation_initiation_client_data and optional telephony_call_config. Exotel phone number create, list, get and update schemas are available, and exotel is added to TelephonyProvider, conversation initiation source and transfer result enums.
Workflow-aware agent transfers: AgentTransfer now allows a nullable agent_id so transfers can stay on the current agent, adds optional node_id to start at a specific node in the destination workflow, and only requires condition. Successful transfer_to_agent tool results can include nullable to_node, aligning transfers with workflow-node targets.
Agent test repeat runs: Run tests on the agent accepts optional repeat_count (integer, 1–20, default 1) to run each test multiple times. When repeat_count is greater than 1, responses include bucketing_status and result_groups for grouped summaries. Unit test create, update and summary schemas add optional conversation_initiation_source so tests can simulate a specific channel.
Conversation filtering: List conversations adds optional workflow_node_entered_id (string) to filter conversations that entered a given workflow node. Text search conversation messages adds optional topic_ids (array of strings) to filter by topic IDs assigned during topic discovery.
Agent versioning query parameters deprecated: enable_versioning on create agent and enable_versioning_if_not_enabled on update agent are marked deprecated. All agents are versioned and these parameters are ignored.
Procedure compiler mode: Removed append from ProcedureCompilerMode.
Workspaces
Revoke API key: Added revoke API key endpoint (DELETE /v1/workspaces/api-keys/revoke) with required api_key_name query parameter to revoke a workspace API key by name. This endpoint is destructive and requires additional account permissions, even though the documentation is public. Contact your ElevenLabs representative to enable it for your account.
Resource access disclosure: Resource access response models add optional access_source (creator, explicit, workspace_default, workspace_admin) so clients can disclose why a user has access to a shared resource.
Speech to Text
Larger upload limit: Convert speech to text now accepts audio and video files up to 5.0GB, increased from 3.0GB.
Dubbing
hCaptcha support: Dub a video or audio file request body adds optional hcaptcha_token (string) for bot protection on dubbing project creation.
Zip render format: RenderType adds zip alongside existing output formats such as mp4, aac, mp3, wav, aaf, tracks_zip and clips_zip.
@elevenlabs/react@1.6.4 - Exposed inputChunkDurationMs for microphone input chunk duration and updated the client dependency to @elevenlabs/client@1.9.0.
