ElevenLabs

Minor Changes

• 1216ded: Add full tool result payload support to onAgentToolResponse.

  The onAgentToolResponse callback now also receives agent_tool_response_full_payload server events, delivering the raw full_tool_result string (capped at 64 KB) alongside the existing summary events. Consumers can distinguish between the two by checking for the presence of full_tool_result on the payload. To receive full payloads, enable the agent_tool_response_full_payload client event in the agent's configuration UI.

  <ConversationProvider
    agentId="…"
    onAgentToolResponse={payload => {
      if ("full_tool_result" in payload) {
        if (payload.truncated) {
          console.warn("full payload truncated to 64 KB");
        }
        console.log(payload.tool_name, payload.full_tool_result);
      } else {
        console.log(payload.tool_call_id, payload.is_error);
      }
    }}
  >
    …
  </ConversationProvider>

  The same callback is available on useConversation, startSession, and the lower-level Conversation.startSession in @elevenlabs/client.

Minor Changes

• 1216ded: Add full tool result payload support to onAgentToolResponse.

  The onAgentToolResponse callback now also receives agent_tool_response_full_payload server events, delivering the raw full_tool_result string (capped at 64 KB) alongside the existing summary events. Consumers can distinguish between the two by checking for the presence of full_tool_result on the payload. To receive full payloads, enable the agent_tool_response_full_payload client event in the agent's configuration UI.

  <ConversationProvider
    agentId="…"
    onAgentToolResponse={payload => {
      if ("full_tool_result" in payload) {
        if (payload.truncated) {
          console.warn("full payload truncated to 64 KB");
        }
        console.log(payload.tool_name, payload.full_tool_result);
      } else {
        console.log(payload.tool_call_id, payload.is_error);
      }
    }}
  >
    …
  </ConversationProvider>

  The same callback is available on useConversation, startSession, and the lower-level Conversation.startSession in @elevenlabs/client.

Patch Changes

• Updated dependencies [1216ded]
  • @elevenlabs/client@1.7.0

Patch Changes

• Updated dependencies [1216ded]
  • @elevenlabs/client@1.7.0

Minor Changes

• 1216ded: Add full tool result payload support to onAgentToolResponse.

  The onAgentToolResponse callback now also receives agent_tool_response_full_payload server events, delivering the raw full_tool_result string (capped at 64 KB) alongside the existing summary events. Consumers can distinguish between the two by checking for the presence of full_tool_result on the payload. To receive full payloads, enable the agent_tool_response_full_payload client event in the agent's configuration UI.

  <ConversationProvider
    agentId="…"
    onAgentToolResponse={payload => {
      if ("full_tool_result" in payload) {
        if (payload.truncated) {
          console.warn("full payload truncated to 64 KB");
        }
        console.log(payload.tool_name, payload.full_tool_result);
      } else {
        console.log(payload.tool_call_id, payload.is_error);
      }
    }}
  >
    …
  </ConversationProvider>

  The same callback is available on useConversation, startSession, and the lower-level Conversation.startSession in @elevenlabs/client.

Patch Changes

• Updated dependencies [1216ded]
  • @elevenlabs/client@1.7.0
  • @elevenlabs/react@1.6.0

Minor Changes

• 1216ded: Add full tool result payload support to onAgentToolResponse.

  The onAgentToolResponse callback now also receives agent_tool_response_full_payload server events, delivering the raw full_tool_result string (capped at 64 KB) alongside the existing summary events. Consumers can distinguish between the two by checking for the presence of full_tool_result on the payload. To receive full payloads, enable the agent_tool_response_full_payload client event in the agent's configuration UI.

  <ConversationProvider
    agentId="…"
    onAgentToolResponse={payload => {
      if ("full_tool_result" in payload) {
        if (payload.truncated) {
          console.warn("full payload truncated to 64 KB");
        }
        console.log(payload.tool_name, payload.full_tool_result);
      } else {
        console.log(payload.tool_call_id, payload.is_error);
      }
    }}
  >
    …
  </ConversationProvider>

  The same callback is available on useConversation, startSession, and the lower-level Conversation.startSession in @elevenlabs/client.

Patch Changes

• Updated dependencies [1216ded]
  • @elevenlabs/types@0.13.0

Patch Changes

• Updated dependencies [84ec003]
• Updated dependencies [3b40bda]
  • @elevenlabs/client@1.6.0
  • @elevenlabs/react@1.5.0

Minor Changes

• 3b40bda: Add an onAgentResponseCorrection callback for agent response correction events.

Minor Changes

• 84ec003: Add native mute/unmute support to Scribe realtime STT integration. RealtimeConnection now exposes mute(), unmute(), and isMuted. The useScribe React hook surfaces these as isMuted state with mute() and unmute() callbacks.
• 3b40bda: Add an onAgentResponseCorrection callback for agent response correction events.

Patch Changes

• Updated dependencies [3b40bda]
  • @elevenlabs/types@0.12.0

Patch Changes

• 6f13d2f: Fix text input submission for IME users by ignoring Enter keydowns while composition is active.
• Updated dependencies [84ec003]
• Updated dependencies [3b40bda]
  • @elevenlabs/client@1.6.0

Minor Changes

• 84ec003: Add native mute/unmute support to Scribe realtime STT integration. RealtimeConnection now exposes mute(), unmute(), and isMuted. The useScribe React hook surfaces these as isMuted state with mute() and unmute() callbacks.
• 3b40bda: Add an onAgentResponseCorrection callback for agent response correction events.

Patch Changes

• Updated dependencies [84ec003]
• Updated dependencies [3b40bda]
  • @elevenlabs/client@1.6.0

What's Changed

• refactor: use urllib.parse for WebSocket URL construction by @kraenhansen in https://github.com/elevenlabs/elevenlabs-python/pull/780
• Add keyterms and no_verbatim to Scribe realtime API by @kraenhansen in https://github.com/elevenlabs/elevenlabs-python/pull/778
• fix: add url_utils.py to .fernignore by @kraenhansen in https://github.com/elevenlabs/elevenlabs-python/pull/782
• :herb: Fern Regeneration -- May 7, 2026 by @fern-api[bot] in https://github.com/elevenlabs/elevenlabs-python/pull/783

Full Changelog: https://github.com/elevenlabs/elevenlabs-python/compare/v2.45.0...v2.46.0

What's Changed

• :herb: Fern Regeneration -- May 7, 2026 by @fern-api[bot] in https://github.com/elevenlabs/elevenlabs-js/pull/380

Full Changelog: https://github.com/elevenlabs/elevenlabs-js/compare/v2.45.0...v2.46.0

Minor Changes

• 8c6213f: Add optional contextId to sendContextualUpdate for deduplicating contextual updates

Patch Changes

• 1153428: Add llm to the typed agent prompt override for conversation sessions.

Patch Changes

• Updated dependencies [8c6213f]
• Updated dependencies [1153428]
• Updated dependencies [33c38e4]
  • @elevenlabs/client@1.5.0
  • @elevenlabs/react@1.4.0

Minor Changes

• 8fe2d6a: Add file upload support to the embedded ConvAI widget

Patch Changes

• Updated dependencies [8c6213f]
• Updated dependencies [1153428]
  • @elevenlabs/client@1.5.0

Minor Changes

• 8c6213f: Add optional contextId to sendContextualUpdate for deduplicating contextual updates

Patch Changes

• 1153428: Add llm to the typed agent prompt override for conversation sessions.
• Updated dependencies [8c6213f]
• Updated dependencies [1153428]
  • @elevenlabs/types@0.11.0

Minor Changes

• 8c6213f: Add optional contextId to sendContextualUpdate for deduplicating contextual updates

Patch Changes

• 1153428: Add llm to the typed agent prompt override for conversation sessions.
• 33c38e4: Allow useScribe microphone deviceId to use full ConstrainDOMString constraints.
• Updated dependencies [8c6213f]
• Updated dependencies [1153428]
  • @elevenlabs/client@1.5.0