# April 7, 2026

### ElevenAgents

- **Scoped conversation analysis**: Evaluation criteria and data collection items can now be scoped to `conversation` (full transcript) or `agent` (only the portion where a specific agent was active). Added `scope` field to `PromptEvaluationCriteria`, `data_collection_scopes` to [agent platform settings](/guides/elevenagents-customization-agent-analysis), and a new `scoped` array of `ScopedAnalysisResult` on the [conversation analysis](https://elevenlabs.io/docs/api-reference/conversations/analysis/run-analysis) response. This is particularly useful for multi-agent workflows where each agent should be evaluated independently.

- **Agent test folder management**: Tests can now be organized into folders. New endpoints for [creating](https://elevenlabs.io/docs/api-reference/tests/test-folders/create), [retrieving](https://elevenlabs.io/docs/api-reference/tests/test-folders/get), [updating](https://elevenlabs.io/docs/api-reference/tests/test-folders/update), and [deleting](https://elevenlabs.io/docs/api-reference/tests/test-folders/delete) test folders, plus [bulk moving](https://elevenlabs.io/docs/api-reference/tests/test-folders/move) tests between folders.

- **Tool and knowledge base overrides in workflows**: Agent workflow node overrides now support `tool_ids` and `knowledge_base` fields in `PromptAgentAPIModelOverrideConfig`, allowing workflow nodes to control which tools and knowledge base documents each sub-agent can access.

- **Response filter `hide_all` mode**: Added `hide_all` option to `ResponseFilterMode`, forcing the system to hide all fields of a tool response from the agent.

- **Visited agents in conversation history**: The [get conversation](/guides/changelog-api-reference-conversations-get) response now includes a `visited_agents` array of `VisitedAgentRef` objects (with `agent_id` and `branch_id`), tracking which agents participated in a multi-agent conversation.

- **Multimodal message support in hooks**: The `useConversationControls` hook now exposes `sendMultimodalMessage`, and the `MultimodalMessageInput` type is exported from `@elevenlabs/client`, making it easier to send images and other multimodal content during conversations.

### Speech to Text

- **Audio duration in responses**: The [convert speech to text](/guides/changelog-api-reference-text-to-dialogue-convert) response now includes an `audio_duration_secs` field, providing the total duration of the transcribed audio without requiring client-side calculation.

### Voices

- **Recording quality and review status**: The [get voice](https://elevenlabs.io/docs/api-reference/voices/get) response now includes `recording_quality` (enum: `studio`, `good`, `ok`, `poor`, `bad`) and `labelling_status` (enum: `in_review`, `review_complete`) fields, providing visibility into voice quality assessment.

### SDK Releases

#### JavaScript SDK

- [v2.42.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.42.0) - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support.

#### Python SDK

- [v2.42.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.42.0) - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support.

#### Swift SDK

- [v3.1.2](https://github.com/elevenlabs/ElevenLabsSwift/releases/tag/v3.1.2) - Fixed ObjC category dispatch for LiveKit delegate methods, resolving potential crashes in Swift-based voice agent integrations.

#### Packages

- [@elevenlabs/client@1.1.1](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/client@1.1.1) - Exposed `sendMultimodalMessage` in the client API and exported the `MultimodalMessageInput` type for sending images and other multimodal content during conversations.

- [@elevenlabs/client@1.1.2](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/client@1.1.2), [@elevenlabs/react@1.0.3](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/react@1.0.3), [@elevenlabs/react-native@1.0.3](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/react-native@1.0.3), [@elevenlabs/types@0.9.1](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/types@0.9.1) - Fixed Node.js ESM compatibility by adding explicit `.js` extensions to all relative imports and setting `"type": "module"` on `@elevenlabs/types`.

- [@elevenlabs/convai-widget-core@0.11.0](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/convai-widget-core@0.11.0) - Added automatic language selection from localStorage history and browser language preferences for the embeddable widget.

### API

:::accordion{title="View API changes"}
## New Endpoints

- [Create folder](https://elevenlabs.io/docs/api-reference/tests/test-folders/create) - `POST /v1/convai/agent-testing/folders`
- [Get folder](https://elevenlabs.io/docs/api-reference/tests/test-folders/get) - `GET /v1/convai/agent-testing/folders/{folder_id}`
- [Update folder](https://elevenlabs.io/docs/api-reference/tests/test-folders/update) - `PATCH /v1/convai/agent-testing/folders/{folder_id}`
- [Delete folder](https://elevenlabs.io/docs/api-reference/tests/test-folders/delete) - `DELETE /v1/convai/agent-testing/folders/{folder_id}`
- [Bulk move tests to folder](https://elevenlabs.io/docs/api-reference/tests/test-folders/move) - `POST /v1/convai/agent-testing/bulk-move`

## Updated Endpoints

### ElevenAgents

- [Create agent](https://elevenlabs.io/docs/api-reference/agents/create), [Get agent](https://elevenlabs.io/docs/api-reference/agents/get), [Update agent](https://elevenlabs.io/docs/api-reference/agents/update)

  - Added `data_collection_scopes` field (object, optional) to `AgentPlatformSettings` for per-item analysis scope control

- [Get conversation](/guides/changelog-api-reference-conversations-get)

  - Added `visited_agents` field (array of `VisitedAgentRef`, optional) tracking agents visited during multi-agent conversations
  - Added `scoped` field (array of `ScopedAnalysisResult`) to conversation analysis response

- [Run conversation analysis](https://elevenlabs.io/docs/api-reference/conversations/analysis/run-analysis)

  - Response now includes `scoped` analysis results with per-agent evaluation breakdowns

- Agent workflow node overrides (`PromptAgentAPIModelOverrideConfig`)

  - Added `tool_ids` field (array of strings, optional) for restricting available tools per workflow node
  - Added `knowledge_base` field (object, optional) for overriding knowledge base per workflow node

- `ResponseFilterMode` enum

  - Added `hide_all` value

- `MockNoMatchBehavior` default

  - Changed default from `call_real_tool` to `raise_error`

- `ClientEvent` enum

  - Added `dtmf_request` value

- Turn metrics
  - Added `convai_tts_cascade` field (string, nullable) to `ConversationTurnMetrics`

### Speech to Text

- [Convert speech to text](/guides/changelog-api-reference-text-to-dialogue-convert)
  - Added `audio_duration_secs` field (number) to response models

### Voices

- [Get voice](https://elevenlabs.io/docs/api-reference/voices/get), [List voices](/guides/changelog-api-reference-voices-search)
  - Added `recording_quality` field (enum: `studio`, `good`, `ok`, `poor`, `bad`, nullable)
  - Added `recording_quality_reason` field (string, nullable)
  - Added `labelling_status` field (enum: `in_review`, `review_complete`, nullable)

### Text to Dialogue

- [Text to dialogue](/guides/changelog-api-reference-text-to-dialogue-convert) response
  - New `ToDialogueSettingsResponseModel` schema with `stability` and `speed` fields
:::

## Related pages

- [Administration](./administration-index.md)
- [API reference](./api-reference-index.md)
- [Changelog](./changelog-index.md)
- [ElevenAgents](./elevenagents-index.md)
- [ElevenAPI](./elevenapi-index.md)
- [ElevenCreative](./elevencreative-index.md)
- [ElevenLabs Documentation Docs](../index.md)
- [General Troubleshooting FAQ](./troubleshooting-index.md)
- [General Website FAQ](./website-index.md)
- [Help Center](./help-center-2-index.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.