SDK Releases: Packages @elevenlabs/client@1.16.0, @elevenlabs/react@1.11.0, @elevenlabs/types@0.18.0
By Steven Van ·
Packages @elevenlabs/client@1.16.0, @elevenlabs/react@1.11.0, @elevenlabs/types@0.18.0, @elevenlabs/react-native@1.2.17…
ElevenLabs shipped a set of SDK and MCP Server updates for its ElevenLabs conversational AI packages, covering streaming reasoning events, widget controls and transcription logging.
- @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 add 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 add a show_resize_button option (and matching show-resize-button embed attribute) 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 add an enableLogging option to Scribe.connect and useScribe. Setting it to false starts an enterprise zero-retention session; the session_started type now reports enable_logging, and the unused disable_logging field was removed.
- MCP Server v0.12.1 carries over the v0.11 tool updates and a dependency refresh that resolves 44 security alerts.
- MCP Server v0.11.0 adds a simulate_conversation tool with configurable simulated-user behaviour, evaluation criteria, transcript output and pass/fail analysis. The speech_to_text tool now defaults to scribe_v2, and voice_clone sends audio file contents instead of path strings.
Full details are in the changelog entry.
ElevenLabs
AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.
View ElevenLabs →