> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

### ElevenAgents

- **Agent version metadata**: Added an API endpoint to retrieve metadata for a specific agent version. The response includes the version ID, agent ID, branch ID, description, sequence number, commit timestamp, parents and access information.
- **Conversation filtering**: Added a `text_only` filter to conversation list and message text search endpoints so developers can narrow results to text-only conversations.
- **Procedure loading**: Added `load_procedure` as a system tool configuration with `ProcedureAtVersion`, and added `skills` to `ProcedureCompilerMode`. `ProcedureSettings.compiler_mode` now defaults to `skills`.
- **Agent configuration updates**: Added `gemini-3.1-flash-lite` and `qwen35-397b-a17b` as LLM options, added `genesys_bot_connector` as a conversation initiation source, added `auto_resolve_after_inactive_minutes` to alerting settings, and added `attributes_to_headers` to SIP trunk configuration.
- **Custom LLM temperature**: Agent prompt temperature can now be set to `null` to omit the temperature field from downstream LLM requests.

### Workspaces

- **Auth connection updates**: Added an API endpoint to update workspace auth connections. The endpoint supports updating basic auth, OAuth2 client credentials and OAuth2 JWT connections. OAuth2 client credentials now support `custom_headers` for token requests.
- **Auth connection types**: Added bearer auth create request support and Slack bot auth response schemas.
- **Workspace resource types**: Added `convai_templates` and `transcription_tasks` to workspace resource types.

### Voice Isolator

- **Video processing status**: Audio isolation history items now include the `video_processing_failed` boolean field.

### SDK Releases

#### Python SDK

- [v2.48.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.48.0) - Regenerated the SDK for the May 18, 2026 API schema, including typed support for workspace auth connection updates, agent version metadata, conversation `text_only` filters, new ElevenAgents configuration fields, updated LLM options and voice isolator history updates. The release also excludes the `speech_engine_custom.py` example from Fern packaging.

#### JavaScript SDK

- [v2.48.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.48.0) - Added environment configuration to conversation initiation data and events, and regenerated the SDK for the May 18, 2026 API schema, including workspace auth connection updates, agent version metadata, conversation `text_only` filters, new ElevenAgents configuration fields, updated LLM options and voice isolator history updates.

#### Packages

- [@elevenlabs/client@1.7.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fclient%401.7.1), [@elevenlabs/react@1.6.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Freact%401.6.1), [@elevenlabs/react-native@1.2.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Freact-native%401.2.1), [@elevenlabs/convai-widget-core@0.12.5](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-core%400.12.5) and [@elevenlabs/convai-widget-embed@0.12.5](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-embed%400.12.5) - Updated the client dependency. `@elevenlabs/client@1.7.1` pins `livekit-client` to `2.16.1` and forces the dual peer connection path to fix WebRTC connection failures with newer LiveKit join protocols.
- [@elevenlabs/types@0.14.0](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Ftypes%400.14.0) - Removed manually maintained types from `@elevenlabs/types`, including `Role`, `Mode`, `Status`, `Callbacks`, `CALLBACK_KEYS`, `DisconnectionDetails`, `MessagePayload` and `AudioAlignmentEvent`. Import those types from `@elevenlabs/client` instead. The types package now contains only generated code.

#### iOS SDK

- [v3.2.0](https://github.com/elevenlabs/elevenlabs-swift-sdk/releases/tag/v3.2.0) - Added support for text-only conversations over WebSockets and fixed message handling.
- [v3.1.5](https://github.com/elevenlabs/elevenlabs-swift-sdk/releases/tag/v3.1.5) - Improved `ConnectionManager` and `DataChannelReceiver` cleanup on deallocation, skipped audio hardware initialization in text-only mode, removed unused code and duplicate agent ID extraction, and bumped visionOS support.

### API

<Accordion title="View API changes">

## New Endpoints

### ElevenAgents

- [Get agent version metadata](/docs/api-reference/agents/versions/get) - `GET /v1/convai/agents/{agent_id}/versions/{version_id}`
  - Added required path parameters `agent_id` (string) and `version_id` (string)
  - Returns `AgentVersionMetadata` with `id`, `agent_id`, `branch_id`, `version_description`, `seq_no_in_branch`, `time_committed_secs`, `parents` and optional nullable `access_info`

### Workspaces

- [Update workspace auth connection](/docs/api-reference/workspace/auth-connections/update) - `PATCH /v1/workspace/auth-connections/{auth_connection_id}`
  - Added required path parameter `auth_connection_id` (string)
  - Added request body union for `UpdateOAuth2ClientCredsRequest`, `UpdateBasicAuthRequest` and `UpdateOAuth2JWTRequest`
  - `UpdateOAuth2ClientCredsRequest` includes optional nullable `custom_headers` as an object with string values
  - Returns the updated auth connection response union

## Updated Endpoints and Schemas

### ElevenAgents

- [List conversations](/docs/api-reference/conversations/list) - `GET /v1/convai/conversations`
  - Added optional nullable query parameter `text_only` (boolean)
- [Text search conversation messages](/docs/api-reference/conversations/messages/text-search) - `GET /v1/convai/conversations/messages/text-search`
  - Added optional nullable query parameter `text_only` (boolean)
- Agent prompt configuration schemas
  - `PromptAgentAPIModel-Input.temperature` and `PromptAgentAPIModel-Output.temperature` now accept `null`
  - Setting `temperature` to `null` omits the temperature field from downstream LLM requests
- `LLM` enum
  - Added `gemini-3.1-flash-lite` and `qwen35-397b-a17b`
- `ConversationInitiationSource` enum
  - Added `genesys_bot_connector`
- Procedure schemas
  - Added `LoadProcedureToolConfig` with `system_tool_type` defaulting to `load_procedure`
  - Added `ProcedureAtVersion` with required `procedure_id`, `name`, `content` and `agent_id`
  - Added `skills` to `ProcedureCompilerMode`
  - Changed `ProcedureSettings.compiler_mode` default from `append` to `skills`
- Alerting schemas
  - Added `auto_resolve_after_inactive_minutes` to `AgentAlertingSettings` as an integer with default `15` and minimum `1`
  - Added nullable `auto_resolve_after_inactive_minutes` to `AgentAlertingMonitorConfig`
- SIP trunk schemas
  - Added `attributes_to_headers` as an object with string values to inbound and outbound SIP trunk request and response models

### Workspaces

- Auth connection schemas
  - Added `CreateBearerAuthRequest` with required `name`, `provider` and `token`
  - Added `SlackBotAuthResponse` with required `name` and `id`, `auth_type` defaulting to `slack_bot_auth`, and `provider` defaulting to `Slack`
  - Added `custom_headers` to `OAuth2ClientCredsResponse` as an object with string values
- `WorkspaceResourceType` enum
  - Added `convai_templates` and `transcription_tasks`

### Voice Isolator

- `AudioIsolationHistoryItemResponseModel`
  - Added required `video_processing_failed` (boolean)

</Accordion>

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.