> This is a page from the ElevenLabs documentation. For an index of the documentation, fetch https://elevenlabs.io/docs/llms.txt.

import { YoutubeEmbed } from "../../../components/YoutubeEmbed";

### Scribe v3

Scribe v3 and Scribe v3 Live, the most accurate ElevenLabs speech recognition models, are now available in the Speech to Text API. [Scribe v3](/docs/overview/models#scribe-v3) (`scribe_v3`) transcribes recorded audio, and [Scribe v3 Live](/docs/overview/models#scribe-v3-live) (`scribe_v3_live`) transcribes in real time. They succeed Scribe v2 and Scribe v2 Realtime, which remain available.

Scribe v3 makes 27% fewer word errors than Scribe v2 on the FLEURS benchmark across 102 languages and labels speakers more accurately. It adds `numbers_format` to write numbers as digits or words, and `secondary_language_codes` for audio that mixes languages. Scribe v3 Live has a 44% lower semantic word error rate than Scribe v2 Realtime on FLEURS across 73 languages. It adds turn prediction, which commits a segment when the speaker has finished their turn instead of at the first pause, a multilingual mode that writes each language in its own script, and a keyterm library of up to 10,000 terms.

<YoutubeEmbed id="e22nKqT-yzg" />

<CardGroup cols={3}>
  <Card title="Scribe v3 models" icon="duotone book" href="/docs/overview/models#scribe-v3">
    Compare Scribe v3 and Scribe v3 Live with Scribe v2 and see how to upgrade.
  </Card>
  <Card
    title="Number and language options"
    icon="duotone code"
    href="/docs/eleven-api/guides/how-to/speech-to-text/batch/number-and-language-options"
  >
    Format numbers and list secondary languages in Scribe v3 transcripts.
  </Card>
  <Card
    title="Turn prediction"
    icon="duotone waveform-lines"
    href="/docs/eleven-api/guides/how-to/speech-to-text/realtime/transcripts-and-commit-strategies#turn-prediction"
  >
    Commit realtime transcripts when the speaker finishes their turn.
  </Card>
</CardGroup>

### Unity SDK

The [ElevenAgents Unity SDK](/docs/eleven-agents/libraries/unity) is now available as the `io.elevenlabs.agents` package, starting with [v0.1.0](https://github.com/elevenlabs/unity/releases/tag/v0.1.0). It supports the Unity Editor, desktop standalone players on macOS, Windows and Linux, and WebGL builds, with iOS, Android and XR in beta. It requires Unity 6.3 LTS or later.

The SDK connects a Unity scene to an agent through a single `Conversation` API. It captures the player's microphone, plays the agent's voice through an `AudioSource` you can position in the scene for spatial audio, and raises transcript, response, mode and tool call events on Unity's main thread. Desktop and mobile builds connect over WebSocket, and WebGL builds can also use WebRTC.

<CardGroup cols={2}>
  <Card title="Unity SDK" icon="duotone code" href="/docs/eleven-agents/libraries/unity">
    Install the package, start a conversation and handle events in a Unity scene.
  </Card>
  <Card title="Client tools" icon="duotone wrench" href="/docs/eleven-agents/customization/tools/client-tools">
    Let the agent call functions in your game code during a conversation.
  </Card>
</CardGroup>

### Workflows as code

**ElevenAgents** workflows can now be built in code with the `Workflow` builder in the Python and JavaScript SDKs, from v2.77.0. Chain `converse`, `tool`, `transfer` and `end` steps with `when`, `on_success` and `go_to` routing, then pass the result as `workflow` to `agents.create()` or `agents.update()`. The builder runs entirely in the SDK, so you can load an agent's workflow, change one node, keep workflows as JSON in version control and still edit them in the visual editor. See [Workflows as code](/docs/eleven-agents/customization/agent-workflows-as-code).

### More agent tools in the hosted MCP server

**Hosted MCP** adds 24 tools for inspecting agents, covering analytics, configuration summaries, insights, alerts, test summaries, branch conflicts and conversation counts. They use the existing `convai_read` and `convai_write` permissions, so connected MCP clients can review an agent the way Architect does. MCP clients can also find and replace or append text in an agent's system prompt or first message, staged in a branch draft until it is published. See [Hosted MCP](/docs/eleven-agents/operate/hosted-mcp).

### All changes

<AccordionGroup>
<Accordion title="ElevenAgents">

- **Workflows as code**: The Python and JavaScript SDKs add a `Workflow` builder for agent workflows. See [Workflows as code](/docs/eleven-agents/customization/agent-workflows-as-code). The workflow editor adds a minimap, zooms out further and has a snap-to-grid toggle, and exposes the subagent `turn.soft_timeout_config` override so dashboard saves no longer remove it.
- **Clone strength and reasoning effort overrides**: Agent `tts.clone_strength`, `clone_strength` on supported voices and a `clone_strength` conversation override are now in the public API. Clients can set `conversation_config_override.agent.prompt.reasoning_effort` once the agent owner enables the **Reasoning effort** override; a level the agent's LLM does not support stops the conversation from starting. Realtime agents show the stability, similarity and clone strength sliders. See [Overrides](/docs/eleven-agents/customization/personalization/overrides).
- **Conversation data**: [List conversations](/docs/api-reference/conversations/list) returns `cost` (credits) and `cost_fiat` (USD), and the conversations table has an optional **Cost** column. Transcript rows on asynchronous channel conversations add `created_at_unix_ms`, and asynchronous conversation metadata adds `integration_trigger_id` and `platform_metadata`, such as the Zendesk `ticket_id`. Post-call `audio` and unredacted audio webhooks include `branch_id`, `version_id` and `environment`.
- **Conversation history limit**: Conversation history, count and search requests from users who can see more than 10,000 agents return `403` `conversation_history_agent_limit_exceeded` unless they filter by agent, instead of returning truncated results.
- **Guardrails**: Triggered guardrails record `execution_mode` (`blocking` or `streaming`) and `guardrail_details`, with the judge's rationale or the classifier verdict, and the conversation transcript shows why a guardrail triggered. Test runs return `triggered_guardrails` and show guardrail triggers in the test transcript. See [Guardrails](/docs/eleven-agents/best-practices/guardrails).
- **Branches**: [List branches](/docs/api-reference/agents/branches/list) and the branch get and update endpoints return `sync_status` for branches that update automatically, with the `outcome` and `attempted_at` time of the last automatic rebase, and the branches table shows its state. Open merge proposals whose target branch is merged and archived are retargeted to the merge target instead of closing. Shareable agent links follow the live traffic split across branches by default, with pinning to the current branch as a separate option.
- **Defaults and models**: Agents created with [Create agent](/docs/api-reference/agents/create) have `workflow.prevent_subagent_loops` on unless the request sets it. When Eleven v3 Conversational fails during a call, agents fall back to Eleven v4 Turbo, Eleven v4 and then Flash, and never to `eleven_v3`, so the voice no longer changes mid-call. The fallback ramp for `gemini-2.5-flash` and `gemini-2.5-flash-lite` now starts on November 15 instead of November 8; the November 30 cutoff is unchanged.
- **Realtime API**: `response.created` and `response.done` always include `response.status_details`. `turn_detection.interrupt_response: false` is honored, and only committed agent text is streamed. `audio/pcm` input at sample rates other than 24000 Hz is rejected with `invalid_audio_format`, and `audio/pcma` is removed from the audio format enum. A `function_call_output` that arrives after its call stopped waiting no longer suppresses the next `response.create`. See [Realtime models](/docs/eleven-agents/customization/realtime-models).
- **Knowledge base**: Sitemap crawls have an **Auto Discover** option that adds new sitemap pages at the folder's auto-sync frequency. Test retrieval in the dashboard covers every retrieval type. The knowledge base tool is registered only when the agent has documents attached. See [Knowledge base](/docs/eleven-agents/customization/knowledge-base).
- **Channels and telephony**: Pre-call webhook `request_headers` accept environment variables, in the API and the dashboard. The Salesforce Cases trigger accepts an optional Reply-To address for email replies. Activating a second Telegram trigger for the same bot returns `409` instead of replacing the first. Redelivered WhatsApp messages no longer get a second reply. Amazon Connect calls no longer end with `408` when the agent pauses. `transfer_to_agent` conditions resolve dynamic variables. WebRTC calls drop stale audio after an interruption, and an inbound audio batch longer than 15 minutes keeps the newest 15 minutes instead of ending the call.
- **Conversation WebSocket**: Text frames that are not a JSON object close the connection with `1008` instead of `1011`. Error closes give end users a generic reason; the detailed reason is sent only to sessions of the agent's owner.
- **Privacy**: Conversation history redaction runs on each turn of asynchronous channels such as Slack, email, WhatsApp text and Telegram before the turn is stored. With history redaction on and audio recording off, `audio` post-call webhooks and storage exports deliver entity-redacted audio. Triage no longer clusters issues from agents in zero retention mode workspaces.
- **Dashboard**: Agents Home (`/app/agents`) opens Architect, and the previous Home dashboard moves to **Dashboards** (`/app/agents/analytics`). Architect's Pro and Lite menu lets you choose a reasoning effort on every plan. Concurrency charts count only voice conversations and no longer change with the chart granularity. Saved views keep every filter, agent search matches partial words in agent names, the Tools tab groups statistics by tool ID, and batch call CSV exports work while calls are still in progress. [Triage tickets](/docs/eleven-agents/operate/triage) can be sorted by `last_reported`. `show_rich_content` carousels accept up to 10 cards, up from 5.
- **Evaluations and analysis**: [Run conversation evaluation](/docs/api-reference/conversations/analysis/run-evaluation) accepts `evaluated_agent_id` and `evaluated_branch_id`, so reruns work for conversations transferred to another agent; rerunning requires edit permission. Analysis item references without a pinned version store `version_id` as `"latest"`. Tool latency statistics used for `auto` pre-tool speech exclude MCP approval waits and failed calls.
- **Fixes**: Conversations on Claude 5.5 models no longer fail with `400` when a response interleaves thinking with text or tool calls. Test runs from the agent editor compile procedures, so structured procedures no longer fail with a transfer error. Merges and rebases no longer report conflicts when both branches made the same procedure change, or on computed test fields and MCP settings. Duplicating an agent remaps procedure references in structured procedure steps. Conference transfers on outbound SIP trunk calls work when the number has no assigned agent. Workflow nodes with tool overrides that previously failed to save now save, new backward transitions no longer show an `exit_slot` error, and `enum` values on LLM expression schemas are kept on save. Calls whose environment does not exist are marked `failed` with the reason in `metadata.error`. Architect works again in the India and Singapore data residency environments.

</Accordion>

<Accordion title="Workspaces">

- **Credit limits**: `PUT /v1/workspace/members/{user_id}/usage-limit` sets the monthly credit limit (`usage_limit`) of a member or service account, or removes it with `null`. Admins can also set it from the **Credit limit** button on the service accounts page. Personal credit limits now count API key and agent usage for every seat type except basic, which still counts only Creative usage. API key and agent usage from before this change is not counted retroactively. See [Members](/docs/overview/administration/workspaces/members).
- **Billing group concurrency**: Enterprise admins can set Text to Speech, Dubbing and Music concurrency limits on billing groups from the group dialogs. See [Billing groups](/docs/overview/administration/workspaces/billing-groups).
- **Architect permission**: Existing full and read-only Agents grants, including grants to Everyone and to groups, now also grant the Architect permission.
- **Auth connections**: OAuth2 JWT auth connections add `jwt_usage`, where `client_authentication` sends the JWT as a `client_assertion` on a `client_credentials` request. OAuth2 JWT and private key JWT connections add `extra_headers` for additional JWT header parameters, such as `x5t`, and the `PS256`, `PS384` and `PS512` algorithms. See [Create auth connection](/docs/api-reference/workspace/auth-connections/create).
- **Webhooks**: OAuth2 webhooks can send client credentials in a Basic authorization header (`token_endpoint_auth_method: client_secret_basic`). `GET /v1/workspace/webhooks?include_usages=true` no longer times out for workspaces with many agents, and webhook retries no longer deliver the same job twice.
- **Audit logs**: The `activity_name` and `class_name` query parameters of [List audit logs](/docs/api-reference/workspace/audit-logs/list) are typed as the `AuditActivityName` and `AuditClassName` enums, which list every accepted value.
- **Fixes**: SCIM requests that time out waiting on a group return `429` with `Retry-After: 5` instead of `500`. Saving the Everyone group no longer fails in workspaces with a permission allowlist.

</Accordion>

<Accordion title="Sound effects">

- **Concurrency limits**: Sound effects have their own per-plan concurrency limits instead of the Text to Speech limit: 4 on Free and Starter, 6 on Creator and Pro, and 8 on Scale and Business. Requests beyond the limit and its reduced-priority queue return `429`. Enterprise customers can request a higher limit. The usage analytics concurrency chart shows Sound effects with its limit. See [Sound effects](/docs/overview/capabilities/sound-effects#concurrency-and-priority).

</Accordion>

<Accordion title="Speech Engine">

- **Authentication**: `auth.enable_auth` (boolean, default `false`) on [Create Speech Engine](/docs/api-reference/speech-engine/create) and [Update Speech Engine](/docs/api-reference/speech-engine/update) requires a signed URL or token to start a conversation. The Security tab has an **Enable authentication** toggle.
- **Sharing**: Workspace sharing endpoints accept a Speech Engine's `seng_` ID, so Speech Engines can be shared in a workspace.

</Accordion>

<Accordion title="Hosted MCP">

- **Agent inspection tools**: 24 tools for agent analytics, configuration summaries, insights, alerts, test summaries, branch conflicts and conversation counts, available with the existing `convai_read` and `convai_write` permissions. See [Hosted MCP](/docs/eleven-agents/operate/hosted-mcp).
- **Prompt editing**: MCP clients can find and replace or append text in an agent's system prompt or first message on a branch. The edit is staged in the branch draft and goes live when the draft is published.
- **Paginated tool listing**: `tools/list` is returned in pages of at most 256 KiB, so MCP clients that reject large listings can connect.
- **Fixes**: OAuth clients that open the authorization page in a popup, such as Gemini Enterprise, can connect. Media in the Flows view loads in ChatGPT.

</Accordion>

<Accordion title="Speech to Text">

- **Scribe v3 and Scribe v3 Live**: [Create transcript](/docs/api-reference/speech-to-text/convert) accepts `scribe_v3` as `model_id`, with new `numbers_format` (`digits` or `words`) and `secondary_language_codes` parameters. The [realtime WebSocket](/docs/api-reference/speech-to-text/v-1-speech-to-text-realtime) accepts `scribe_v3_live`, with `commit_strategy=turn_prediction`, `multilang_mode` and a keyterm library of up to 10,000 terms. Scribe v2 and Scribe v2 Realtime remain available. See [Models](/docs/overview/models#scribe-v3).
- **Timestamps with background filtering**: The [realtime WebSocket](/docs/api-reference/speech-to-text/v-1-speech-to-text-realtime) accepts `include_timestamps` together with `filter_background_audio`, with timestamps mapped to the original audio.
- **Lower partial latency**: Realtime partial transcripts are sent as soon as they are produced, removing up to 100 ms of delay. `turn_probability` on partial transcripts is rounded to two decimal places.
- **EU data residency**: `transcript_edit` is available in the EU data residency environment.
- **Fixes**: Realtime transcripts no longer contain emotion labels such as `{neutral}`.

</Accordion>

<Accordion title="Voices">

- **Voice Library matches**: When Instant Voice Clone samples match a protected voice that is available in the Voice Library, [Create IVC voice](/docs/api-reference/voices/ivc/create) and `POST /v2/voices/create-preview-from-samples` return `library_voice_match`, with `library_voice_id` and `public_owner_id`. If the clone is blocked, the `403` response includes the same object in `detail.data`. Pass both IDs to `POST /v1/voices/add/{public_user_id}/{voice_id}` to add the library voice instead.
- **Voice categories**: The `VOICE_CATEGORY` enum no longer lists `famous`.
- **Fixes**: Instant Voice Clone drafts are stored per user and workspace, and the page no longer loops on an old draft. Adding a library voice to My Voices no longer reports success without listing the voice.

</Accordion>

<Accordion title="Dubbing">

- **Failed languages**: Target languages that cannot start, for example because the quota is exceeded, are marked `FAILED` instead of staying `PENDING`, and targets pending for more than 7 days fail.
- **Short sources**: Sources shorter than 0.1 seconds are rejected with `source_too_short` before any charge.
- **Verified clones**: Dubbing accepts a workspace's own verified voice clones that match a protected voice instead of blocking them.
- **Legacy manual mode**: The **Manual mode** option is renamed **Legacy manual mode** and is shown only when Dubbing v1 is selected.

</Accordion>

<Accordion title="Studio">

- **Aspect ratios**: Projects can use 3:4 and 4:3 aspect ratios, and media in those ratios starts new projects at the matching ratio.
- **Subtitle timing**: SRT and VTT exports apply paragraph trims, so subtitles match the exported audio.
- **Faster blank projects**: Blank audiobook projects are created without a wait, and blank `eleven_v3` projects no longer get the sample template.
- **Fixes**: Replacing the content of a large project with `POST /v1/studio/projects/{project_id}/content` no longer fails with `500`. IME input, such as Japanese, is no longer committed early or mid-word in the editor. **Pause after paragraph** pauses at the real end of a paragraph that is still loading, and no longer pauses as soon as you press Play at the start of a paragraph.

</Accordion>

<Accordion title="Image and video">

- **Image editor**: Rotating a layer rotates its selection box, masks sit in their own draggable box, and text and shape layers can be rotated, masked and recolored.
- **Flows**: Figma `.fig` imports keep small icons whole and keep drop shadows, rounded clipping and borders of stroke-only frames. The Text to Speech node offers the full 0 to 100% Stability range for Eleven v4. Seedance 2.5 unlocks the aspect ratio when a video reference is selected, and dropped assets are arranged in a grid.

</Accordion>

<Accordion title="Voice Changer and Voice Isolator">

- **Video in Voice Changer**: Voice Changer in the app keeps video uploads as video. History opens a viewer with the original and converted audio tracks, and the converted video can be downloaded as MP4.
- **Fixes**: [Voice Isolator](/docs/api-reference/audio-isolation/convert) returns `400` `invalid_audio` instead of `500` for `pcm_s16le_16` uploads with an odd number of bytes.

</Accordion>

<Accordion title="Text to Speech">

- **Pronunciation previews**: The pronunciation dictionaries dialog has a model picker for previewing rules, instead of always previewing with `eleven_turbo_v2`.

</Accordion>

<Accordion title="Billing">

- **Voice library surcharge**: The agents voice library surcharge is charged per voice, so usage analytics attributes it to each voice instead of "No voice".

</Accordion>

<Accordion title="Other products">

- **AI Speech Classifier**: The classifier accepts video files and checks their audio track.

</Accordion>

<Accordion title="SDK releases">

#### JavaScript SDK

- [v2.77.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.77.0) - Added a `Workflow` builder, exported from the package root, that builds agent workflows with chained calls and produces the `workflow` value for `agents.create()` and `agents.update()`. See [Workflows as code](/docs/eleven-agents/customization/agent-workflows-as-code).

#### Python SDK

- [v2.77.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.77.0) - Added the `Workflow` builder in `elevenlabs.agent_workflows`, which builds agent workflows with chained calls and produces the `workflow` value for `agents.create()` and `agents.update()`. Speech Engine create and update accept the `auth` parameter.

#### ElevenLabs CLI

- [v1.9.1](https://github.com/elevenlabs/cli/releases/tag/v1.9.1) - `agents workflow diagram` draws bare workflow files exported by the SDK `Workflow` builders. `onboard` waits up to 30 minutes for sign-in approval instead of 5, retries a token request that could not connect, and reports a copied key that `/v1/user` refuses as "couldn't be checked" instead of belonging to another account.

#### Unity SDK

- [v0.1.0](https://github.com/elevenlabs/unity/releases/tag/v0.1.0) - First release of the ElevenAgents Unity SDK (`io.elevenlabs.agents`), installed from the git URL through the Unity Package Manager. Adds the `Conversation` session API, conversation events, messaging, client tools, audio and device controls, a native WebSocket transport for the Editor and desktop players, and a WebGL transport with WebSocket and WebRTC. Requires Unity 6.3 LTS or later. See [Unity SDK](/docs/eleven-agents/libraries/unity).

#### Packages

- [@elevenlabs/client@1.35.0](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fclient%401.35.0) and [@elevenlabs/types@0.29.0](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Ftypes%400.29.0) - `overrides.tts.modelId` is typed as `ConversationConfigOverrideTtsModelId`, which lists the documented ElevenAgents TTS models. Other strings are still accepted. `model_id` is added to `conversation_config_override.tts` only when `modelId` is set.
- [@elevenlabs/convai-widget-core@0.25.0](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-core%400.25.0) - The voice and text mode toggle is a Voice/Text segmented control, with `voice_mode_label` and `text_mode_label` text contents. A `default-size` attribute (`compact` or `expanded`) sets the size the chat opens at. A "new messages" button with a count appears when messages arrive while the transcript is scrolled up, labeled with the `new_message` and `new_messages` text contents.
- [@elevenlabs/convai-widget-core@0.25.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-core%400.25.1) - Carousels show up to 10 cards, up from 5.
- [@elevenlabs/react@1.21.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Freact%401.21.1), [@elevenlabs/react-native@1.2.38](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Freact-native%401.2.38), [@elevenlabs/convai-widget-embed@0.25.0](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-embed%400.25.0) and [0.25.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-embed%400.25.1) - Updated to the latest `@elevenlabs/client` and widget releases.

</Accordion>

<Accordion title="API changes">

## New endpoints

### Workspaces

- `PUT /v1/workspace/members/{user_id}/usage-limit` - Set or clear the monthly credit limit of a workspace member or service account. Requires `usage_limit` (integer, minimum 0, or `null` to remove the limit). Admins only.

## Updated endpoints

### ElevenAgents

- [Create agent](/docs/api-reference/agents/create) and the agent get and update endpoints
  - TTS configuration adds `clone_strength` (number, default `0`), supported voices add nullable `clone_strength` (number), and TTS conversation and workflow overrides add nullable `clone_strength`. The override config adds `tts.clone_strength` (boolean, default `false`).
  - Prompt overrides add nullable `reasoning_effort` (`LLMReasoningEffort`), and the override config adds `prompt.reasoning_effort` (boolean, default `false`). `conversation_config_override` on the `/v1/convai/conversation` WebSocket accepts `agent.prompt.reasoning_effort` and `tts.clone_strength`.
  - Pre-call webhook `request_headers` values accept `ConvAIEnvVarLocator` in addition to strings and secret locators.
  - Analysis item references (`AttachedUserEvaluationRef`, `AttachedUserDataCollectionRef`) default `version_id` to `"latest"` and it is no longer nullable.
  - `SearchStrategy` defaults to `semantic`.
  - `DataCollectionValueSchema.allowed_values_dynamic_variable` is deprecated; use `allowed_values` instead.
- [List conversations](/docs/api-reference/conversations/list) - Added nullable `cost` (integer) and `cost_fiat` (number) to each conversation summary.
- [Get conversation details](/docs/api-reference/conversations/get)
  - Asynchronous conversation metadata adds nullable `integration_trigger_id` (string) and `platform_metadata`.
  - Transcript rows add nullable `created_at_unix_ms` (integer), also in test responses.
  - Triggered guardrails add nullable `execution_mode` (`streaming` or `blocking`) and `guardrail_details` (LLM, classifier or unknown verdict).
  - `AgentDefinitionSource` adds `mcp`.
- [Run conversation evaluation](/docs/api-reference/conversations/analysis/run-evaluation) - Added optional `evaluated_agent_id` and `evaluated_branch_id` (string).
- [List branches](/docs/api-reference/agents/branches/list) and the branch get and update endpoints - Added nullable `sync_status` with `last_attempt` (`outcome`: `succeeded`, `conflict`, `no_common_ancestor`, `rejected` or `error`, and `attempted_at` in Unix seconds).
- Test runs (`POST /v1/convai/agents/{agent_id}/run-tests` and the [test invocation endpoints](/docs/api-reference/tests/test-invocations/get)) - Added `triggered_guardrails` (array).
- Triage tickets (`GET /v1/convai/triage-tickets` and `GET /v1/convai/agents/{agent_id}/triage-tickets`) - The sort enum adds `last_reported`.
- Realtime client secrets (`POST /v1/convai/realtime/client_secrets`) - `AudioFormat` no longer lists `audio/pcma`.

### Speech Engine

- [Create Speech Engine](/docs/api-reference/speech-engine/create) and [Update Speech Engine](/docs/api-reference/speech-engine/update) - Added optional `auth` with `enable_auth` (boolean, default `false`). Speech Engine responses include `auth`.

### Voices

- [Create IVC voice](/docs/api-reference/voices/ivc/create) - Added nullable `library_voice_match` with `library_voice_id` and `public_owner_id` (string).
- `VOICE_CATEGORY`, used by the dubbing similar voices endpoint, removed `famous`.

### Workspaces

- [Create auth connection](/docs/api-reference/workspace/auth-connections/create) and the auth connection get and update endpoints
  - OAuth2 JWT connections add `jwt_usage` (`authorization_grant`, the default, or `client_authentication`).
  - OAuth2 JWT and private key JWT connections add `extra_headers` (map of strings), and `algorithm` adds `PS256`, `PS384` and `PS512`.
- [List audit logs](/docs/api-reference/workspace/audit-logs/list) - `activity_name` and `class_name` query parameters changed from string to the `AuditActivityName` and `AuditClassName` enums.

</Accordion>
</AccordionGroup>