The voiceover engine behind most faceless YouTube and audiobook stacks. Voice cloning, multilingual, low-latency streaming.
Scribe v2 Medical is now generally available as a specialized batch speech recognition model for medical and clinical audio. It maintains the same billing rate as Scribe v2 and supports keyterm prompting, entity detection, speaker diarization, and no-verbatim mode. Pass scribe_v2_medical as the model_id parameter.
Outbound calls through Twilio can now detect whether they reach a human or answering machine. Configure detection mode to trigger early detection or wait for voicemail greetings to complete. Results arrive via a new answering_machine_detection webhook event.
Agent response WebSocket events include optional attachments with URL, name, and optional MIME type. Enables agents to send files and documents to users during conversations.
Outbound telephony configurations now support Twilio answering machine detection with two modes: early human-or-machine verdict or waiting for voicemail greeting to finish. Detection results are delivered via the new answering_machine_detection webhook event.
agent_response WebSocket events now include an optional attachments field, allowing agents to send files with metadata including URL, filename, and MIME type.
ElevenAgents gained workspace-wide conversation ticket management with cursor pagination and filtering, dynamic variable filters supporting comparison operators (eq, gt, gte, lt, lte), and Twilio answering machine detection for outbound calls with early or post-greeting detection modes. Agent responses now support file attachments, and knowledge base RAG queries include source URLs.
Agent conversation configuration now accepts dtmf_input_settings allowing agents to receive phone keypad input with configurable timeout, hash terminator, and optional redaction from logs. Enables IVR-style interaction patterns in agent conversations.
Agent conversation configuration now supports DTMF (phone keypad) input through optional dtmf_input_settings. Developers can configure digit timeout, use # as a terminator, and optionally redact keypad entries from transcripts and logs.
Conversation transcript entries now include file_inputs array containing details about every attached file (ID, name, MIME type, and URL). This enables developers to access complete context about files used during agent conversations.
ElevenAgents conversations now support DTMF (phone keypad) input with configurable digit timeout and optional # terminator. Developers can also redact keypad entries from transcripts and logs.