跳到导航

更新日志

October 19, 2026

Eleven Realtime

Eleven Realtime is a new family of models for ElevenAgents voice agents, rolling out gradually across workspaces. Each one is a complete voice agent configuration. You pick one model, and ElevenLabs handles the LLM, Speech to Text and Text to Speech settings behind it. Your agent’s system prompt, voice, tools and knowledge base work the same as before.

There are two to choose from. Eleven Realtime v1 Mini (eleven_realtime_v1_mini) is the default, and it’s the fastest and cheapest. Eleven Realtime v1 Max (eleven_realtime_v1_max) reasons before it answers, so use it when your agent has complex instructions or multi-step tool calls.

If you’ve already built on OpenAI’s Realtime API, you don’t need to rewrite your client. The events and the WebSocket transport are the same, so you change the endpoint and the session configuration. Your backend calls Create realtime client secret to get a short-lived secret, and the browser uses it to connect directly.

Realtime models

Choose a Realtime model and configure an agent’s voice mode.

OpenAI Realtime API compatibility

Connect an existing OpenAI Realtime client to ElevenLabs.

Create realtime client secret

Review the request and response for minting client secrets.

Realtime Translation

Realtime Translation turns speech in one language into speech in another while the speaker is still talking. It’s a WebSocket API, available now for enterprise workspaces.

You open a connection with a target_language and a voice_id, then stream audio in. You get translated speech back in that voice. You don’t have to say which language the speaker is using, because it’s detected automatically, but you can set source_language if you know it. Along the way, the server also sends live transcripts of the original speech and the translated text, for example to show captions.

eagerness controls the tradeoff between speed and quality. high starts translating soonest, and low waits for more of the sentence. The translated voice uses Eleven v4 Turbo by default, and you can switch to eleven_v3 or eleven_flash_v2_5 with tts_model_id. For sensitive conversations, set enable_zrm=true to use Zero Retention Mode.

Realtime Translation WebSocket

Review the connection parameters and message types.

Models

Compare the TTS models available for translated speech.

Zero Retention Mode

Keep transcripts and translations out of logs and history.

Video to Music

Video to Music writes a soundtrack for your video. The Video to music API is now available: you upload a video and get back music that fits it, without writing a music prompt from scratch. Use it to score product videos, ads and social clips.

You can send up to 10 video files (200 MB combined). They’re joined in order and scored as one video. To steer the result, add a text description and up to 10 style tags.

Three options are worth knowing. use_audio_as_reference takes the genre, BPM, instruments and mood from the video’s own audio. add_sfx adds sound effects that match the video. separate_tracks returns the music and the sound effects as separate files in a ZIP, so you can mix them yourself.

Video to music API reference

Review the request parameters and response format.

Music overview

Learn what Eleven Music can generate and how it can be used.

ElevenAgents

  • Alerts: Alerts notify a workspace when agent error rates exceed a threshold or rise sharply above their recent baseline. Monitors cover conversation failures, tool failures, webhook errors, guardrail triggers, call initiation errors and evaluation success scores, and run with default thresholds without any setup. Agent-level thresholds and notifiers can be set through platform_settings.alerting on Update agent. Notifications can be delivered as webhooks, to Slack or to PagerDuty.
  • Guardrails generally available: Guardrails are no longer in alpha.
  • Workspace environments: Environments for environment variables can now be managed through the API with List environments, Create environment and Delete environment. A variable without a value for an environment falls back to its production value. Deleting an environment removes its values from all variables, and production cannot be deleted.
  • Answering machine detection actions: Twilio answering machine detection settings on Outbound call and Submit batch call accept actions, a list of rules that pair an action (hang_up) with the answered_by verdicts that trigger it, such as machine_start or fax. Verdicts without a rule leave the call running.
  • New LLMs: Agents can use gemini-4-argon, claude-opus-4-6 and the ElevenLabs-hosted nemotron-35-super-vl-nvfp4. See Models.
  • Authored-only workflow reads: Get agent and Update agent accept include_procedure_generated_workflow_elements. Set it to false to receive only the workflow nodes and edges you authored, excluding the ones compiled from structured procedures. Defaults to true, so existing callers are unchanged.
  • Branch rebasing from any branch: Rebase branch and Preview rebase accept an optional source_branch_id to pull changes from a branch other than main.
  • Delete agents used as subagents: Delete agent accepts force. When true, the agent is deleted even if other agents use it as a subagent, and it is removed from those agents and their branches.
  • Sort agents by last update: List agents accepts sort_by=updated_at, and each agent summary includes updated_at_unix_secs, the last time the main branch or agent-level settings changed.
  • Google Calendar event updates: The Google Calendar integration adds google_calendar_update_event and google_calendar_delete_event tools. Both are privileged tools that can change or cancel any event on the connected calendar.

Music and Sound Effects

  • Zero Retention Mode: Music generation, composition plan, stem separation and video to music endpoints, plus Sound Effects, accept enable_logging=false to use Zero Retention Mode. Zero Retention Mode is available to enterprise customers. Music requests that set store_for_inpainting=true are rejected in this mode.
  • WAV output for sound effects: Sound Effects accepts wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000 output formats.

Speech Engine

  • 40-minute conversations: Speech Engine supports conversations of up to 40 minutes. The default limit remains 10 minutes. Raise conversation.max_duration_seconds to allow longer conversations.
  • Sort by last update: List Speech Engines accepts sort_by=updated_at, and each summary includes updated_at_unix_secs.

Dubbing

  • Subtitles for dubbed languages: Dubbing project language outputs (GET /v1/dubbing/project/{project_id}/language/{language_id}) include subtitles, a signed URL to the translated lines as WebVTT subtitles timed to the source speech. The URL expires one hour after it is issued.

Voices

  • Resubmittable voice reviews: Voice sharing review_status adds declined_resubmittable for declined voices that can be resubmitted for review.

Workspaces

  • Disable service account API keys: Disable service account API key disables a service account API key without changing its other settings. It remains available after a workspace downgrades from a plan that includes service accounts.
  • Group concurrency limits: List workspace groups and List service accounts return group_concurrency_limit, group_dubbing_concurrency_limit and group_music_concurrency_limit for each group, and group permissions add all_resources_access.

SDK releases

JavaScript SDK

  • v2.74.0 - Added client.conversationalAi.realtime.createClientSecret for the Realtime API, with the RealtimeModel and OpenAI-compatible session configuration types, and an environments client with list, create and delete. Also adds force on agent deletion, sourceBranchId on branch rebase and rebase preview, includeProcedureGeneratedWorkflowElements on agent reads, enableLogging on Music and Sound Effects methods, WAV output formats for Sound Effects, service account API key disable, and Twilio answering machine detection actions.
  • v2.73.0 - Added createAndWait helpers for Flows image, video and Text to Speech generations and template runs (client.flows.templates.runs.createAndWait). They create the request and poll until it completes or fails, pacing requests with the server’s Retry-After header. A failed result is returned rather than thrown, and waitTimeoutInSeconds throws FlowsWaitTimeoutError if the work is not finished in time. The regenerated client adds the Video to music add_sfx, separate_tracks and use_audio_as_reference options.

Python SDK

  • v2.74.1 - music.compose_detailed now accepts and forwards enable_logging, which the custom wrapper previously dropped, so Zero Retention Mode works with this method.
  • v2.74.0 - Added client.conversational_ai.realtime.create_client_secret for the Realtime API and an environments client, with the same regenerated API changes as JavaScript SDK v2.74.0.
  • v2.73.0 - Added create_and_wait helpers for Flows image, video and Text to Speech generations and template runs, for both sync and async clients, with wait_timeout_in_seconds and min_poll_interval_in_seconds options and a FlowsWaitTimeoutError exported from elevenlabs.flows_custom. Type checkers such as pyright now resolve client.webhooks.construct_event, client.speech_to_text.realtime, client.text_to_speech.convert_realtime and the custom Music methods. Includes the same regenerated API changes as the JavaScript SDK.
  • v2.73.1 - Fixed the test suite on Python 3.13 and later, and added Python 3.13 and 3.14 to CI.

ElevenLabs CLI

  • v1.7.0 - Regenerated API commands, adding environments, realtime client secrets and service account API key disabling.
  • v1.6.0 - Added create-and-wait commands for flows image, flows video, flows text-to-speech and flows templates runs. Each command returns a finished result, with --wait-timeout and --min-poll-interval options.
  • v1.5.1, v1.5.2, v1.5.3 and v1.6.1 - Bug fixes for onboarding, including Windows support.

Packages

API

New endpoints

ElevenAgents

  • Create realtime client secret - POST /v1/convai/realtime/client_secrets - Create an ephemeral client secret for browser-based Realtime API sessions. Accepts an optional session (OpenAI-compatible session configuration with model of eleven_realtime_v1_mini (default) or eleven_realtime_v1_max, instructions, audio, tools, turn_detection and max_duration_seconds from 60 to 7,200, default 600) and optional expires_after with required seconds (integer). Returns value (string), expires_at (integer) and the echoed session.

  • List environments - GET /v1/convai/environments - List the workspace environments, including production. Each environment has name, nullable updated_at_unix_secs and nullable created_by_user_id.

  • Create environment - POST /v1/convai/environments - Create an environment with a required, unique name (string). Returns 409 if the name is taken.

  • Delete environment - DELETE /v1/convai/environments/{environment} - Delete an environment and remove its values from all environment variables. Returns 204.

Workspaces

  • Disable service account API key - POST /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}/disable - Disable a service account API key without changing its other settings.

Updated endpoints

ElevenAgents

  • Get agent, Update agent, Preview rebase and Preview merge
    • Added optional include_procedure_generated_workflow_elements (boolean, default true). When false, the returned workflow contains only authored nodes and edges, without those generated from structured procedures.
  • Create agent, Get agent and Update agent
    • The llm enum adds gemini-4-argon, claude-opus-4-6 and nemotron-35-super-vl-nvfp4.
    • TTS configuration effects removes the deprecated seed field.
  • Delete agent - Added optional force (boolean, default false).
  • List agents - sort_by adds updated_at. Agent summaries add required updated_at_unix_secs (integer).
  • Rebase branch and Preview rebase - Added optional source_branch_id (string). Defaults to the agent’s main branch.
  • Outbound call, Submit batch call and Get batch call
    • Twilio machine detection configuration adds actions, an array of rules with required action (hang_up) and required answered_by (array of human, fax, unknown, machine_start, machine_end_beep, machine_end_silence or machine_end_other). Each action can appear in at most one rule.
  • Get conversation details
    • Transcript tool calls add nullable tool_id (string). It is not set for tools without an ID, such as system tools.
    • Turn metrics add nullable voice_id (string).
    • Tool results add nullable to_agent and to_node (string).
    • WhatsApp conversation info adds nullable recipient with nullable phone and bsuid (string), and nullable call_permission_request with required state (blocked, sent, accepted or declined) and nullable requested_at_unix (integer).
    • The platform charge category enum adds v3_addon, v4_addon and rag_addon.
  • Get ticket, List tickets and List workspace tickets
    • Ticket responses add required status_changes, an array of objects with status, nullable changed_by_user_id (string) and changed_at_unix_secs (integer).

Text to Speech and Text to Dialogue

Music

Sound Effects

  • Create sound effect
    • Added optional enable_logging query parameter (boolean, default true).
    • output_format adds wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000.

Speech Engine

  • List Speech Engines - sort_by adds updated_at. Summaries add required updated_at_unix_secs (integer).

Speech to Text

  • Create transcript and Get transcript - Edited transcripts add required, read-only edited_text (string), matching text and the edited_text field of the realtime edited_transcript event.

Dubbing

  • GET /v1/dubbing/project/{project_id}/language and GET /v1/dubbing/project/{project_id}/language/{language_id} - Language outputs add nullable subtitles (string, signed URL).

Voices

Workspaces

  • List workspace groups and List service accounts
    • Groups add nullable group_concurrency_limit, group_dubbing_concurrency_limit and group_music_concurrency_limit (integer or unlimited).
    • Group permissions add all_resources_access.
October 12, 2026

ElevenAgents

  • Merge and search triage tickets: Merge tickets folds up to 50 open tickets from the same agent into one target ticket. Merged tickets keep the status merged and reference the target through merged_into_ticket_id. List tickets and List workspace tickets add a case-insensitive search parameter that matches ticket titles, descriptions, comments and turn comments, and each result includes a search_match excerpt showing where the query matched.
  • Workflow End node outcomes: Workflow End nodes accept an outcome of success (default) or failure, so a workflow can record whether a conversation ended successfully. The conversation error type adds workflow_end_failure.
  • Call queueing enabled for new agents: New agents are created with call queueing enabled unless platform_settings.queueing_config.enabled is set explicitly. Existing agents keep their current setting.
  • Post-call audio webhook retries: When Enable retries is on, post_call_audio webhooks are retried on the same schedule as transcription webhooks. Audio payloads over 50 MiB are not retried, and queued audio retries are capped at 400 MiB per webhook.
  • Strict tool overrides: The conversation override tool_ids_strict makes an overridden tool_ids list the complete set of tools available in the conversation, including tools on workflow nodes. It is ignored when set on the agent itself.
  • Widget end confirmation: The widget can ask users to confirm before ending a chat or call. Enable it with end_confirmation_enabled in the widget configuration or the end-confirmation attribute.

Text to Speech

  • Audio effects: Text to Speech and Text to Dialogue requests accept an optional audio_effects object. It applies a filter preset, perceived distance, a reverb environment, a looped background noise bed and stereo panning to the generated audio. List valid preset, environment and background noise IDs with GET /v1/audio-effects/catalog. Reverb and non-zero panning produce stereo audio and are rejected for ulaw_*, alaw_* and pcm_* output formats. Effects do not change the cost of a request.

Speech to Text

  • Turn prediction commit strategy: The realtime Speech to Text WebSocket adds turn_prediction as a commit_strategy value. In addition to silence-based segmentation, it commits a segment as soon as the model predicts the speaker has finished their turn. It is the default for models that predict turns, and partial transcripts from those models include turn_probability. See transcripts and commit strategies.

Voices

  • Voice collections API: Voice collections can now be managed through the API. Create, list, update and delete collections, and add or remove voices. See List voice collections.

Workspaces

  • Basic seat fallback: Update member accepts allow_downgrade_to_basic_seat. When unlocking a user whose original seat type has no seats available, the user is moved to a basic seat instead of the request failing.
  • Workspace ID on user: Get user returns the workspace_id of the workspace the API key belongs to.

SDK releases

JavaScript SDK

  • v2.72.0 - Added clients for voice collections, the audio effects catalog and triage ticket merging. Text to Speech and Text to Dialogue methods accept audio_effects, triage ticket list methods add search and filters, and the realtime Speech to Text client adds the turn_prediction commit strategy.

Python SDK

  • v2.72.0 - Added clients for voice collections, the audio effects catalog and triage ticket merging. Text to Speech and Text to Dialogue methods accept audio_effects, triage ticket list methods add search and filters, and the realtime Speech to Text client adds the turn_prediction commit strategy. play() and save() now accept any iterable of audio chunks, such as a list or tuple. RealtimeEvents.CLOSE handlers receive a dictionary with the WebSocket close code and reason; handlers without parameters continue to work.

ElevenLabs CLI

  • v1.5.0 - Regenerated API commands, adding voice collections, the audio effects catalog, triage ticket merging and agent merge proposals.

Packages

  • @elevenlabs/client@1.27.0 and @elevenlabs/react@1.17.0 - Added a previousText option to Scribe.connect() and useScribe() in microphone mode. The text is sent with the first audio chunk to give the model context, such as existing document text, for casing, punctuation and sentence continuation. MediaDeviceOutput now receives libsampleratePath, so output resampling uses the same custom libsamplerate bundle path as MediaDeviceInput.
  • @elevenlabs/react-native@1.2.29 - Updated to @elevenlabs/client@1.27.0 and @elevenlabs/react@1.17.0.
  • @elevenlabs/convai-widget-core@0.19.0 and @elevenlabs/convai-widget-embed@0.19.0 - Added an optional confirmation dialog before ending a chat or call, enabled with the end-confirmation attribute or end_confirmation_enabled config, with customizable text. Added carousel rich content with scrollable item cards that can include an image, subtitle, description and actions. Carousels remain in the transcript after a reply, without their actions. Rich content is now shown during voice calls when the transcript is visible.

API

New endpoints

ElevenAgents

  • Merge tickets - POST /v1/convai/triage-tickets/{agentqa_ticket_id}/merge - Merge open tickets into the target ticket. Requires source_ticket_ids (string array, 1–50 items) and returns the target ticket.

Voices

  • List voice collections - GET /v1/voices/collections - List the voice collections the caller can access, sorted by title.
  • Create voice collection - POST /v1/voices/collections - Create a collection with required title and icon (string, maximum 1,000 characters each).
  • Get voice collection - GET /v1/voices/collections/{collection_id} - Retrieve a collection with its title, icon and the caller’s permission_on_resource (admin, editor, commenter or viewer).
  • Update voice collection - PATCH /v1/voices/collections/{collection_id} - Update the optional title or icon.
  • Delete voice collection - DELETE /v1/voices/collections/{collection_id}
  • Add voice to collection - POST /v1/voices/collections/{collection_id}/voice/{voice_id}
  • Remove voice from collection - DELETE /v1/voices/collections/{collection_id}/voice/{voice_id}

Audio effects

  • GET /v1/audio-effects/catalog - List the available filter_presets, environments and background_noises. Each entry has an ID, a name and a nullable description.

Updated endpoints

ElevenAgents

  • Create agent, Get agent and Update agent
    • Workflow End nodes add outcome (success or failure, default success). The field is required in responses.
    • Standalone workflow agent nodes and agent transfer configurations add nullable branch_id (string) to target a specific branch of the destination agent. When unset, the transfer follows the target agent’s traffic deployment. Transfer tool results add a configured branch reason.
    • Prompt override configurations add tool_ids_strict (boolean, default false).
    • TTS configuration effects add pan (number, -1 to 1, default 0). The seed field is deprecated and has no effect.
  • Get widget config - Added end_confirmation_enabled (boolean, default false).
  • List tickets
    • Added optional search (string, maximum 200 characters) and merged_into_ticket_id (string) query parameters.
    • Ticket responses add nullable merged_into_ticket_id and nullable search_match with field (title, description, comment or turn_comment), snippet, highlight_start, highlight_end and nullable turn_index.
  • List workspace tickets - Added optional agent_id, sources, priorities, sort_by (created_at or priority, default created_at), owner_user_id, issue_type, label, merged_into_ticket_id and search query parameters.
  • List tests - Added optional created_by_user_id (string). Use @me for the authenticated user.
  • List test invocations - Added optional test_id (string), version_id (string), start_time and end_time (integer, Unix seconds, inclusive) query parameters.
  • Update agent branch - Added optional auto_rebase (boolean). Branch responses add auto_rebase (boolean, default false).
  • Get conversation details
    • Twilio, SIP trunk and Exotel phone call metadata add nullable call_result with answered, voicemail, busy, no_answer and failed values.
    • Batch call metadata adds nullable cold_attempt (integer) and nullable conversation_type (initial, retry, callback or redirect).
    • The conversation error type adds workflow_end_failure.
  • Knowledge base auto-sync auto_discover is deprecated and no longer has any effect.

Text to Speech

  • Create speech, Stream speech, Create speech with timing and Stream speech with timing
    • Added optional nullable audio_effects with filter_preset_id (string), distance (number, 0–1, default 0), environment_id (string), background_noise_id (string), send_level (number, 0–1, default 1) and pan (number, -1 to 1, default 0).
    • Unknown effect IDs return 404. Stereo effects return 400 for ulaw_*, alaw_* and pcm_* output formats.

Text to Dialogue

Speech to Text

  • Realtime Speech to Text
    • The commit_strategy query parameter adds turn_prediction, alongside manual and vad.
    • partial_transcript messages add optional turn_probability (number), sent only for models that predict turns.

Music

  • POST /v1/music/video-to-music - Responses add a song-id header with the ID of the generated song.

History

Workspace and user

  • Update member - Added optional allow_downgrade_to_basic_seat (boolean, default false).
  • Get user - Added required workspace_id (string).
  • Service account API key permissions add voice_collections_read and voice_collections_write.
October 5, 2026

ElevenAgents

  • Structured procedures compile on save and publish: Update agent and Create agent draft now compile and validate structured procedures automatically. Integrations no longer need to call the compile endpoint or manually update the generated workflow. Invalid procedures return per-procedure errors as 400 procedure_validation_failed. Agents without structured procedures are unaffected.
  • Compile procedures endpoint is legacy: Compile procedures is marked legacy and should not be used by new integrations. It remains available for existing callers.
  • Merge proposals: Merge proposals are available in alpha. Teams can open a proposal for an agent branch, review configuration changes and test results, leave comments or approval decisions, and merge approved changes into a target branch. See Merge proposals.

SDK releases

JavaScript SDK

  • v2.71.0 - Added clients for agent merge proposals, deployment history, test invocation cancellation and Speech Engine duplication. The release also adds triage ticket priorities and sorting, batch call export limits, gpt-6.1-sol, claude-sonnet-5-5, Eleven v4 agent voice models and current agent configuration types.

Python SDK

  • v2.71.0 - Added clients for agent merge proposals, deployment history, test invocation cancellation and Speech Engine duplication. The release also adds triage ticket priorities and sorting, batch call export limits, gpt-6.1-sol, claude-sonnet-5-5, Eleven v4 agent voice models and current agent configuration types.

Swift SDK

  • v3.4.0 - Dynamic variables now preserve native JSON types when sent in conversation initiation data.

Packages

API

New endpoints

ElevenAgents

  • Create a merge proposal - POST /v1/convai/agents/{agent_id}/merge-proposals - Create a proposal with required source_branch_id, target_branch_id and title fields, plus an optional description, reviewer IDs and triage ticket ID.
  • List merge proposals - GET /v1/convai/agents/{agent_id}/merge-proposals - List proposals with status, source branch, target branch and text filters, plus cursor pagination.
  • Get a merge proposal - GET /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id} - Retrieve a proposal and its review, comment and outcome details.
  • Update a merge proposal - PATCH /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id} - Update its title, description or requested reviewers, or close it without merging.
  • Review a merge proposal - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/reviews - Submit an approved or changes_requested decision with an optional comment.
  • Comment on a merge proposal - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/comments - Add a Markdown comment of up to 4,096 characters.
  • Merge a merge proposal - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/merge - Merge the source branch and optionally control forced conflict resolution and source branch archival.
  • List agent deployments - GET /v1/convai/agents/{agent_id}/deployments - List current and historical branch traffic splits with page-based pagination.
  • Cancel a test invocation - POST /v1/convai/test-invocations/{test_invocation_id}/cancel - Cancel a running test invocation.

Speech Engine

  • Duplicate a Speech Engine - POST /v1/speech-engine/{speech_engine_id}/duplicate - Duplicate a Speech Engine and optionally assign the copy a new name.

Updated endpoints

ElevenAgents

  • Create agent, Get agent and Update agent
    • Added gpt-6.1-sol and claude-sonnet-5-5 to the LLM enum.
    • Added eleven_v4 and eleven_v4_turbo to the conversational TTS model options. The default changed from eleven_flash_v2 to eleven_v4_turbo.
    • Agent transfers and standalone workflow agent nodes add optional preserve_voice_settings (boolean, default false) to retain the base voice, TTS model and voice settings after a transfer.
    • Skip-turn tool configurations add optional wait_timeout_secs (number, default -1). A value of -1 keeps the agent silent until the caller speaks.
    • Post-call webhook configurations add optional exclude_transcript (boolean, default false) to omit turn-by-turn transcripts from JSON transcription webhooks.
    • Conversation history redaction configurations add optional excluded_data_collection_ids (string array, maximum 50) to preserve selected extracted values while redacting their rationales.
    • Client tool response_timeout_secs now accepts -1 to wait indefinitely when expects_response is enabled.
  • List tickets
    • Added optional priorities (array) with low, medium, high and urgent values.
    • Added sort_by with created_at and priority values; the default is created_at.
    • Ticket responses now require title, nullable priority, and a priority_changes array. Ticket creation and update requests can set priority, and ticket status adds cancelled.
  • List tools - Added optional nullable used_by_agent_id (string) to return tools referenced by an agent’s main branch.
  • Export batch call results - Added optional nullable limit (integer, minimum 1) to export only the first recipients as a column preview.
  • List test invocations and Get test invocation
    • Test invocation summaries add required cancelled_count (integer) and optional cancelled (boolean, default false).
    • Test run status adds cancelled.
  • Get conversation details - Transcript entries add optional nullable platform_event with user_turn_timeout and skip_turn_wait_elapsed values.
  • Get agent version metadata - Added optional nullable merged_authors, an array describing the people who published changes merged into the main branch.
  • Get crawl job - Removed the deprecated max_depth response field.
September 28, 2026

Eleven v4 和 Eleven v4 Turbo

Eleven v4 和 Eleven v4 Turbo 现已推出。Eleven v4 可在超过 90 种语言中提供更高质量、更具表现力的语音，以及更出色的语音克隆。Eleven v4 Turbo 属于同一模型系列，适用于实时应用，中位推理延迟约为 100 ms。

内容创作和长音频可通过文本转对话 API 使用 eleven_v4。智能体和交互式应用可通过文本转对话 WebSocket 使用 eleven_v4_turbo。

Eleven v4 概览

对比两个模型版本、语音克隆行为、设置和支持的语言。

文本转对话 API

使用 Eleven v4 生成高质量对话。

实时流式传输

通过 WebSocket 连接流式传输 Eleven v4 Turbo 对话。

语音转文字

  • 转录编辑：批量和实时转录现可接受最长 2,000 个字符的自然语言编辑指令。批量响应会在 edited_transcript 中返回结果，实时会话则会发出 edited_transcript 事件。有关不兼容项、响应处理和定价，请参阅批量和实时指南。

ElevenAgents

  • 智能体模型：在支持的智能体 LLM 选项中新增 gpt-6-sol、gpt-6-luna、glm-52、deepseek-v41-flash、claude-opus-5 和 claude-opus-5-5。
  • 智能体测试用量：测试调用摘要可包含总积分和美元价格。单次测试运行可包含积分和计费明细。

Flows

  • 模板 API：新增用于列出和获取已发布 Flows 模板、启动模板运行及获取运行结果的端点。运行可指定已发布版本，并将最终结果发送至配置的 webhook。

文本转对话

  • 生成连续性：文本转对话请求可使用前文或后文以及请求 ID，以保持多次生成之间的连续性。
  • 专业音色模式：文本转对话请求可使用专业语音克隆的即时语音克隆版本，以降低延迟或提升表现力。

SDK 发布

JavaScript SDK

  • v2.70.0 - 新增批量和实时语音转文字转录编辑类型、测试调用摘要的 branchId 筛选和费用字段、知识库自动发现、文本转对话 usePvcAsIvc 以及 deepseek-v41-flash 智能体模型。

Python SDK

  • v2.70.0 - 新增批量和实时语音转文字转录编辑类型、测试调用摘要的 branch_id 筛选和费用字段、知识库自动发现、文本转对话 use_pvc_as_ivc 以及 deepseek-v41-flash 智能体模型。

ElevenLabs CLI

  • v1.4.0 - 修复使用明确 API 密钥的请求同时发送已存储 OAuth 凭据的问题，该问题会导致身份验证失败。为反馈命令组添加说明，并为生成的智能体技能添加报告缺失功能的说明。使用 Flows 模板端点和当前架构类型重新生成 API 客户端。

API

新增端点

Flows

  • 列出模板 - GET /v1/flows/templates - 列出已发布模板及其可运行版本。
  • 获取模板 - GET /v1/flows/templates/{template_id} - 获取模板及其可运行版本。
  • 创建模板运行 - POST /v1/flows/templates/{template_id}/runs - 使用输入值、可选版本和可选 webhook 启动模板运行。
  • 列出模板运行 - GET /v1/flows/templates/{template_id}/runs - 使用游标分页和可选版本筛选列出模板运行。
  • 获取模板运行 - GET /v1/flows/templates/{template_id}/runs/{run_id} - 获取模板运行及其输出状态。

更新的端点

语音转文字

  • 将语音转换为文字 - POST /v1/speech-to-text
    • 新增可选可空 transcript_edit（字符串），可接受最长 2,000 个字符的自然语言编辑指令。
    • 响应新增可选可空 edited_transcript。编辑成功时包含必填 kind: "transcript" 和 text 字段。编辑失败时包含必填 kind: "error"、error_type: "edit_failed" 和 message 字段。
  • 实时语音转文字接受 transcript_edit（字符串），并发出包含必填 text 和 edited_text 字段的 edited_transcript 事件。

ElevenAgents

  • 创建智能体、获取智能体和更新智能体
    • 在 LLM 枚举中新增 gpt-6-sol、gpt-6-luna、glm-52、deepseek-v41-flash、claude-opus-5 和 claude-opus-5-5。
    • 告警监控项新增可选可空 enabled（布尔值），用于控制监控项是否可发送通知。
  • 列出对话和文本搜索
    • data_collection_params 和 dynamic_variable_params 新增 neq 和 in 运算符。in 的值使用竖线分隔。
    • evaluation_params 接受 success、failure 或 unknown 作为结果值。
  • 智能搜索 - GET /v1/convai/conversations/messages/smart-search
    • 新增可选可空 branch_id（字符串）。
  • 列出测试调用 - GET /v1/convai/test-invocations
    • 新增可选可空 branch_id（字符串）。
    • 测试调用摘要新增可选可空 credits_used（整数）和 total_price（数字）。
  • 获取测试调用 - GET /v1/convai/test-invocations/{test_invocation_id}
    • 单次测试运行新增可选可空 credits_used（整数）和 charging（ConversationChargingCommonModel）。
  • 模拟对话和模拟对话流
    • 将可选 new_turns_limit 的默认值从 10,000 改为 100，并将最大值设为 100。
  • 创建爬取任务和获取爬取任务
    • 新增可选 auto_discover（布尔值，默认 false），用于在自动同步期间跟踪链接并添加新发现的页面。这需要 enable_auto_sync: true。
  • 刷新知识库文档 - POST /v1/convai/knowledge-base/{documentation_id}/refresh
    • AutoSyncInfo 新增可选 auto_discover（布尔值，默认 false），用于指示刷新时是否爬取并添加新发现的页面。
  • 列出 MCP 服务器工具 - GET /v1/convai/mcp-servers/{mcp_server_id}/tools
    • 响应新增可选 tool_approval_statuses（数组）。每项包含必填 tool_id（字符串）和 state（up_to_date、needs_review 或 not_approved），以及可选的审批策略和已批准定义字段。

文本转对话

  • 将文本转换为对话、流式转换文本为对话、转换并附带时间戳和流式转换并附带时间戳
    • 新增可选 use_pvc_as_ivc（布尔值，默认 false），用于使用专业语音克隆的即时语音克隆版本。
    • 新增可选可空 previous_text 和 future_text（字符串，最长 100 个字符），以及 previous_request_ids 和 next_request_ids（字符串数组，最多 3 个 ID），用于保持生成连续性。
    • 可选 settings 对象新增可空 similarity（数字，0–1，默认 0.75）。

文本转语音

Flows

声音设计

工作区

  • 创建服务账户 API 密钥 - POST /v1/service-accounts/{service_account_user_id}/api-keys
    • 为企业版服务账户 API 密钥新增可选可空 tts_concurrency_limit、music_concurrency_limit 和 dubbing_concurrency_limit（整数）。
  • 更新服务账户 API 密钥 - PATCH /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}
    • 新增可选 tts_concurrency_limit、music_concurrency_limit 和 dubbing_concurrency_limit。每个字段可接受整数、clear、no_update 或 null，默认值为 no_update。

模型

  • 列出模型 - GET /v1/models
    • 弃用必填 max_characters_request_free_user 和 max_characters_request_subscribed_user。这些字段不会强制执行；请改用 maximum_text_length_per_request。
September 23, 2026

图像和视频

  • Sora 2 和 Sora 2 Pro 已停用：OpenAI 将于 2026 年 9 月 24 日停止 Sora API 服务。两个模型已从图像和视频模型选择器中移除，并将于该日期停止生成。现有生成内容仍可在历史记录中查看。使用 Sora 节点的 Flows 和模板需切换到其他视频模型，例如 Gemini Omni 1.1 Flash，才能再次运行。
  • Seedance 1.5 Pro 已弃用：ByteDance 将于 2026 年 11 月 11 日停止 Seedance 1.5 Pro 服务。该模型不再提供给新的生成任务，并将于该日期停止运行。请改用 Seedance 2.0 模型。
September 21, 2026

ElevenAgents

  • 并行工具调用：智能体提示词配置现包含 enable_parallel_tool_calls（布尔值，默认 true）。启用后，支持的模型可在一次轮次中执行多个工具。
  • 智能体模型：智能体 LLM 选项新增 gpt-6-astra。
  • 告警：智能体告警现支持 Slack 频道，以及 PagerDuty 和 webhook 通知器。
  • 电话号码搜索：新增基于游标分页的电话号码端点，可按提供商、外呼支持、已分配智能体和分支、标签及电话号码筛选。

图像和视频

  • GPT Image 2.5 模型：图像生成现支持 gpt-image-2.5-flare 和 gpt-image-2.5-sunburst。两个模型均最多支持 10 张参考图像，质量级别最高可选 max，支持 14 种固定宽高比及 auto，并可输出 1K、2K 或 4K。

语音引擎

  • 级联超时：语音引擎创建和更新请求现接受 cascade_timeout_seconds（数字，2–15，默认 4），用于控制 ElevenLabs 在重试前等待上游语音引擎的时长。

文本转语音

  • 多上下文轮次边界：现会在该轮次的每个缓冲字节后发送 is_final_audio_for_turn 标记，包括 MP3 和 Opus 输出。客户端无需切换到 PCM，即可将此标记用作精确的轮次边界。

SDK 发布

JavaScript SDK

  • v2.69.0 - 在实时文本转语音封装器中新增 transcriptEdit，编辑后的文本通过 edited_transcript 事件发送。修复带数据驻留后缀的 API 密钥的语音引擎 JWT 验证问题。新增 phoneNumbers.listV2 和 Flows 模板方法，可列出和获取模板，以及列出、创建和获取运行。重新生成了 GPT Image 2.5、Slack 智能体告警、并行工具调用、gpt-6-astra、服务账户 API 密钥并发限制、Music 零保留、对话筛选器和 MCP 工具审批状态的客户端和类型。

Python SDK

  • v2.69.0 - 在实时文本转语音封装器中新增 transcript_edit，编辑后的文本通过 edited_transcript 事件发送。修复带数据驻留后缀的 API 密钥的语音引擎 JWT 验证问题，并让 play 在 ffplay 失败时抛出错误。新增 phone_numbers.list_v2 和 Flows 模板方法，可列出和获取模板，以及列出、创建和获取运行。重新生成了 GPT Image 2.5、Slack 智能体告警、并行工具调用、gpt-6-astra、服务账户 API 密钥并发限制、Music 零保留、对话筛选器和 MCP 工具审批状态的客户端和类型。

ElevenLabs CLI

  • v1.3.2 - 新增可选 --intent 元数据，以收集 CLI 使用反馈。新增 elevenlabs feedback missing-capability，用于报告 CLI 不支持的工作流程。

API

新增端点

ElevenAgents

  • 列出电话号码页面 - GET /v1/convai/v2/phone-numbers
    • 新增可选 page_size（整数，1–1,000，默认 100）和 cursor（可为空的字符串）分页参数。
    • 新增可选 search、label、phone_number、provider、supports_outbound、agent_id、branch_id、sort_by 和 sort_direction 筛选器。sort_by 接受 label 或 phone_number；sort_direction 默认为 asc。
    • 响应包含必填 phone_numbers（数组）、可选且可为空的 next_cursor（字符串）和 has_more（布尔值，默认 false）。

更新的端点

ElevenAgents

  • 创建智能体、获取智能体 和 更新智能体
    • 提示词配置新增 enable_parallel_tool_calls（布尔值，默认 true）。工作流程覆盖项接受可为空的布尔值。
    • LLM 枚举新增 gpt-6-astra，包括对话发起覆盖项。
    • 告警集成通知器现使用 integration_type 选择 pagerduty 或 slack。Slack 通知器需要 connection_id 和 channel_id（字符串）；channel_id 接受 1–64 个字符。
  • 列出对话和解析对话引用
    • data_collection_params 不再接受 missing 运算符。请使用空值来匹配未收集该字段的对话。
    • dynamic_variable_params 中的空值可匹配未设置该变量的对话。
  • 创建语音引擎、获取语音引擎 和 更新语音引擎
    • 新增 cascade_timeout_seconds（数字，2–15）。创建请求默认值为 4，更新请求接受可为空的值，响应要求包含该字段。

图像和视频

  • 创建图像生成 - POST /v1/flows/image
    • 为 gpt-image-2.5-flare 和 gpt-image-2.5-sunburst 新增请求变体。
    • 两种变体均需要 prompt 和 model_id，最多接受 10 个 images，并新增 resolution（1K、2K 或 4K，默认 1K）。
    • quality 接受 low、medium、high、xhigh 或 max，默认为 high。aspect_ratio 接受 auto 和 14 种固定比例，默认为 16:9。

配音

知识库

  • 创建爬取任务 - POST /v1/convai/knowledge-base/crawl
    • 已弃用 max_depth（整数，默认 3）。该字段现无实际作用，且不再有最小或最大限制。
    • 爬取任务元数据不再要求 max_depth。

用户

架构变更

文本转语音

  • 多上下文 WebSocket audio 和 final 消息现将 is_final_audio_for_turn 定义为：在该轮次的所有缓冲字节均已发送后发生。
September 14, 2026

ElevenAgents

  • 通话排队和等待音频：为达到并发上限的智能体新增通话排队。排队中的来电者会听到等待音频，并持续收到 queue_status 事件，直至接入或超时。新增 API 方法可上传或删除自定义等待音频。
  • 测试版本元数据：智能体测试结果现在会标识其运行所针对的智能体版本，以及是否包含草稿更改。调用摘要还会标识部分重新提交是否针对不同版本运行。
  • 模型和账户元数据：智能体 LLM 配置现支持 gemini-3.8-flash。WhatsApp 账户响应会标识账户使用 Cloud API 还是共存注册流程。

音乐

  • Music v2.5 API 支持：音乐端点和 SDK 现支持 music_v2_5。乐曲方案生成分块最多支持 6,132 个字符，最多 30 行，每行 200 个字符。

SDK 发布

JavaScript SDK

  • v2.68.0 - 新增上传和删除智能体等待音频的方法。重新生成了通话排队、流程引用、草稿分支创建、RAG 查询限制、测试版本元数据、gemini-3.8-flash 和 music_v2_5 的类型。

Python SDK

  • v2.68.0 - 新增同步和异步上传、删除智能体等待音频的方法。重新生成了通话排队、流程、草稿分支创建、RAG 查询限制、测试版本元数据、gemini-3.8-flash 和 music_v2_5 的类型。compose_detailed 封装器现支持所有已生成的音乐模型 ID，以及基于提示词和分块的乐曲方案。

iOS SDK

  • v3.3.1 - 现按 response_id 而非 event_id 协调智能体消息，可保留工具调用前后的多个响应，并防止流式片段或修正内容附加到错误的消息。

ElevenLabs CLI

  • v1.3.0 - 为生成的 API 命令新增可选 --intent 元数据。新增 elevenlabs feedback missing-capability，用于报告 CLI 不支持的工作流程。

软件包

API

新增端点

ElevenAgents

  • 上传智能体等待音频 - POST /v1/convai/agents/{agent_id}/hold-audio
    • 接受必填的 hold_audio_file（二进制）作为 multipart 表单数据。文件必须为 MP3 或 WAV，最大 40 MB、180 秒。
    • 返回必填的 agent_id（字符串）和 hold_audio（AgentHoldAudioConfig）。等待音频对象需要 audio_path、audio_url、original_filename（字符串）、duration_secs（数字）和 size_bytes（整数）。
  • 删除智能体等待音频 - DELETE /v1/convai/agents/{agent_id}/hold-audio
    • 删除自定义片段，使排队来电者听到默认等待音。
    • 返回必填的 agent_id（字符串）。

更新的端点

ElevenAgents

  • 创建智能体、获取智能体 和 更新智能体
    • 新增可选 platform_settings.queueing_config（AgentQueueingConfig），包含 enabled（布尔值，默认 false）和 wait_timeout_seconds（整数，1–1,800，默认 180）。
    • 队列配置响应包含只读、可为空的 hold_audio（AgentHoldAudioConfig）。智能体响应还包含可选 default_hold_audio_url（字符串）。
  • 获取对话 - GET /v1/convai/conversations/{conversation_id}
    • 元数据新增可选、可为空的 queue_wait_secs（数字）。排队时间不计入 call_duration_secs 和计费时长。
  • 创建智能体分支 - POST /v1/convai/agents/{agent_id}/branches
    • 新增可选 include_draft（布尔值，默认 false）。设为 true 时，从分支顶端创建的分支会包含调用方的草稿流程集。
  • 列出流程以及流程创建、获取和草稿端点
    • 列表项新增可选 referenced_tool_ids、referenced_kb_ids、referenced_procedure_ids 和 referenced_dynamic_variables（字符串数组）。
    • 智能体和合并预览响应新增可选 procedures，这是一个以流程 ID 为键的映射。
  • 列出测试调用 - GET /v1/convai/test-invocations
    • 新增可选、可为空的 search（字符串），可按名称筛选测试和文件夹。
  • 在智能体上运行测试和获取测试调用
    • 测试套件调用和单元测试运行响应新增可选、可为空的 version_id（字符串）以及可选 ran_against_draft（布尔值，默认 false）。
    • 调用摘要还新增可选 runs_diverged_from_version（布尔值，默认 false）。
  • POST /v1/convai/agents/{agent_id}/knowledge-base/rag-query
    • 请求正文新增可选、可为空的查询专用覆盖项 max_documents_length（整数，1–50,000）和 max_retrieved_rag_chunks_count（整数，1–20）。
  • 获取 WhatsApp 账户 - GET /v1/convai/whatsapp-accounts/{phone_number_id}
    • 新增可选 account_type（WhatsAppAccountType，默认 cloud_api）。可选值为 cloud_api 和 coexistence。
  • 计算预期 LLM 用量 - POST /v1/convai/agent/{agent_id}/llm-usage/calculate
    • LLMUsageCalculatorLLMResponseModel 新增必填 price_per_message（数字）。

音乐

  • MusicModelID 为 POST /v1/music/video-to-music、POST /v1/music/plan、创作音乐、POST /v1/music/detailed、POST /v1/music/detailed/stream、POST /v1/music/stream、POST /v1/music/upload 和 POST /v1/music/finetunes 新增 music_v2_5。
  • 对于 POST /v1/music/plan、POST /v1/music、POST /v1/music/detailed、POST /v1/music/detailed/stream、POST /v1/music/stream 和 POST /v1/music/upload，GenerationChunk.text 的 maxLength 从 6,000 个字符提高到 6,132 个字符。段落名称可包含 1–100 个字符，分块最多可包含 30 行，每行 200 个字符。

架构变更

ElevenAgents

  • 实时服务器事件新增 queue_status。其必填 queue_status_event.status 接受 waiting、admitted 或 timed_out；timed_out 会先于 WebSocket 关闭代码 4300 发生。等待音频仍作为常规 audio 事件发送。
  • LLM 枚举新增 gemini-3.8-flash，包括对话发起覆盖项。
  • 对话系统工具结果联合类型新增 start_procedure_success、start_procedure_error、end_procedure_success 和 end_procedure_error。
  • FeaturesUsageCommonModel 新增可选 freeform_procedure 和 structured_procedure 功能状态。
September 11, 2026

Scribe v2 Medical

Scribe v2 Medical 现已正式发布。这是一款专为医疗和临床音频设计的批量语音识别模型，计费标准与 Scribe v2 相同。

在创建转录文本时，将 model_id 设为 scribe_v2_medical。关键词提示、实体检测、说话人分离和非逐字模式的使用方式与 Scribe v2 相同。

模型

模型 ID、功能以及适合使用 Scribe v2 Medical 的场景。

创建转录文本

将 model_id 设为 scribe_v2_medical，即可转录音频。

September 7, 2026

ElevenAgents

  • 工作区范围的对话工单：新增列出工作区工单，可获取有访问权限的智能体中的对话分诊工单。可按状态或负责人筛选，并使用游标分页，每页最多获取 100 个工单。
  • 动态变量对话筛选：列出对话和文本搜索对话消息现接受可重复的 dynamic_variable_params 筛选条件。使用 name:op:value 格式，op 可为 eq、gt、gte、lt 或 lte；比较运算符要求值为数值。
  • Twilio 答录机检测：外呼电话和批量呼叫配置现支持可选的 twilio_machine_detection。选择 enable 可尽早判断是人工还是机器，选择 detect_message_end 则等待语音信箱问候语结束。结果将通过新的 answering_machine_detection webhook 事件送达。
  • 数据收集值约束：数据收集属性现可使用 allowed_values 指定一个包含允许值的动态变量。此前的 allowed_values_dynamic_variable 字段已弃用。
  • 智能体元数据：列出智能体分支响应现会指明草稿的创建时间，以及它是否早于分支最新提交。智能体和语音引擎摘要现在要求提供 voice_id。
  • 知识库源 URL：智能体 RAG 查询分块现包含必需且可为 null 的 source_url，其中包含 URL 文档的追踪 URL。
  • 智能体响应附件：agent_response WebSocket 事件现包含可选的 attachments。每个附件都需要 url 和 name，并可包含 mime_type。

工作区

  • API 密钥平台限制：服务账号 API 密钥响应现可包含企业版 platform_limits，涵盖额度、专业语音克隆，以及 TTS、配音和音乐的并发限制。

SDK 发布

JavaScript SDK

  • v2.67.0 - 在对话列表和文本搜索请求中添加 dynamicVariableParams。重新生成 Twilio 答录机检测、数据收集值约束、API 密钥平台限制、智能体分支草稿元数据和知识库源 URL 的类型。

Python SDK

  • v2.67.0 - 在同步和异步对话列表及文本搜索方法中添加 dynamic_variable_params。重新生成 Twilio 答录机检测、数据收集值约束、API 密钥平台限制、智能体分支草稿元数据和知识库源 URL 的类型。实时文本转语音客户端不再将内部 omit sentinel 传递给连接。

ElevenLabs CLI

  • v1.2.0 - 添加 elevenlabs say 命令及其智能体技能，重新生成 API 命令绑定，并将 eleven_v3 设为默认 TTS 模型。

软件包

API

新增端点

ElevenAgents

  • 列出工作区工单 - GET /v1/convai/triage-tickets
    • 列出调用方有权访问的所有智能体中的对话分诊工单，按创建时间从近到远排序。
    • 添加可选的 page_size（整数，1–100，默认 100）、status（AgentConversationTicketStatus）、assignee_user_id（字符串或 unassigned）和 cursor（字符串）查询参数。
    • 返回 GetAgentConversationTicketsPageResponseModel。

已更新端点

ElevenAgents

  • 列出对话 - GET /v1/convai/conversations
    • 添加可选且可为 null 的 dynamic_variable_params（可重复字符串数组）。每个值使用 name:op:value 格式，其中 op 为 eq、gt、gte、lt 或 lte。
  • 文本搜索对话消息 - GET /v1/convai/conversations/messages/text-search
    • 添加具有相同语法的可选且可为 null 的 dynamic_variable_params（可重复字符串数组）。
  • Twilio 外呼、SIP 中继外呼、Exotel 外呼和提交批量呼叫
    • telephony_call_config 现使用独立的输入和输出 schema。
    • 添加可选且可为 null 的 twilio_machine_detection（TwilioMachineDetectionConfig）。其 mode 接受 enable 或 detect_message_end，默认值为 enable。非 Twilio 服务商和呼入电话会忽略此设置。
  • 导入电话号码 - POST /v1/convai/phone-numbers
    • 为 Twilio API 密钥导入添加可选且可为 null 的 account_auth_token（字符串），用于验证呼入 webhook 签名。

Schema 变更

ElevenAgents

  • WebhookEventType 新增 answering_machine_detection。
  • AgentBranchSummary 新增可选且可为 null 的 draft_created_at（整数）和可选的 draft_is_behind_tip（布尔值，默认 false）。
  • AgentKnowledgeBaseRagChunkResponseModel 新增必需且可为 null 的 source_url（字符串）。
  • AgentSummaryResponseModel 和 SpeechEngineSummaryResponse 新增必需的 voice_id（字符串）。
  • AnalysisProperty 新增可选且可为 null 的 name（字符串）和 allowed_values（AllowedValues）。LiteralJsonSchemaProperty 也新增 allowed_values。两者均弃用 allowed_values_dynamic_variable。
  • DataCollectionResultCommonModel 新增可选且可为 null 的 name（字符串）。
  • WorkspaceApiKeyResponseModel 新增可选且可为 null 的 platform_limits（PlatformLimits）。
  • MCP 工具 Icon 新增可选且可为 null 的 theme（light 或 dark）。
  • SMBToolConfig 新增 send_custom_email、create_service_quote_request 和 create_product_quote_request 参数变体。
  • Webhook 查询参数 schema 和电话呼叫配置现使用独立的输入和输出模型。
  • agent_response WebSocket 事件新增可选的 attachments（数组）。每项都需要 url 和 name（字符串），并接受可选的 mime_type（字符串）。

ElevenCreative

  • ReferenceVideo.studio_clip 现使用 StudioClipLocator 替代 StudioClipReference。字段和线缆格式保持不变。
August 31, 2026

ElevenAgents

  • 电话按键输入：智能体对话配置现支持可选的 dtmf_input_settings，用于 DTMF 输入。可配置数字输入超时、使用 # 作为结束符，并从转录文本、日志和分析中隐藏按键输入内容。
  • 对话附件历史记录：获取对话的转录条目现包含 file_inputs，这是一个数组，包含每个附件文件的 ID、名称、MIME 类型和 URL。
  • 智能体标签筛选：列出智能体现接受可选的 tags 查询参数。重复该参数可匹配带有任一指定标签的智能体。
  • 批量活动上下文：获取对话现可通过可为 null 的 campaign 元数据识别批量呼叫，其中包含必需的 campaign_id 和 campaign_lead_id。

音乐

配音

  • 项目分页行为：列出配音项目和列出语言目标现会将 page_size 限制在 1–100。项目状态筛选新增 queued，且两个端点均说明如何使用 next_cursor 获取下一页。

SDK 发布

JavaScript SDK

  • v2.66.0 - 为 sendMultimodalMessage 添加 fileIds，一条消息现在可包含多个文件附件。

Python SDK

  • v2.66.0 - 为 send_multimodal_message 添加 file_ids，一条消息现在可包含多个文件附件。

Android SDK

  • v0.12.2 - 连接会话事件时保留 onUnhandledClientToolCall 回调。需要响应的未处理客户端工具调用现在会收到自动错误响应，而不再处于未解决状态。

ElevenLabs CLI

  • v1.1.0 - 重新生成 API 命令绑定，并为 ElevenAgents workflow 添加命令级请求归因。这些命令会将 cmd/<command> 追加到 CLI 的 User-Agent，从而区分 agents push 和 agents create 等 workflow 发出的请求。

软件包

API

已更新端点

ElevenAgents

  • 列出智能体 - GET /v1/convai/agents
    • 添加可选且可为 null 的 tags（字符串数组）。重复该查询参数可匹配任一指定标签。
  • 创建智能体、获取智能体和更新智能体
    • 添加可选且可为 null 的 conversation_config.conversation.dtmf_input_settings（DTMFInputConfig）。支持 dtmf_input_timeout（数值，0.5–10 秒，默认 2）、hash_terminator（布尔值，默认 true）和 redact_input（布尔值，默认 false）。
    • 在电话号码转接配置中添加可选的 sip_refer_play_dialtone（布尔值，默认 true）。将其设为 false，可在 SIP REFER 转接完成期间保持原始通话线路静音。
    • 开始和结束流程系统工具现可接受 ProcedureVersionRef 或 ProcedureDraftRef。草稿引用需要 procedure_id（字符串），并将 version_id 设为 null。
  • 获取对话 - GET /v1/convai/conversations/{conversation_id}
    • 在转录条目中添加 file_inputs（ConversationHistoryTranscriptFileInputResponseModel 数组）。每项都需要 file_id、original_filename、mime_type 和 file_url（字符串）。
    • 在批量呼叫元数据中添加可选且可为 null 的 campaign（BatchCallingCampaignInformation）。该对象需要 campaign_id 和 campaign_lead_id（字符串）。
    • 向 ChatSourceMedium 添加 dtmf。
  • 对话分诊工单问题类型新增 incorrect_information、documentation_gap、platform_bug 和 wrong_action。

音乐

  • 详细生成音乐（POST /v1/music/detailed）和流式生成音乐及详情（POST /v1/music/detailed/stream）
    • 添加可选的 with_waveform_visual（布尔值，默认 false）。
    • 详情响应新增可为 null 的 waveform_visual（整数数组），每秒采样 4 次，取值范围为 -1000 到 1000。
  • 上传音乐 - POST /v1/music/upload
    • 在响应中添加可选的 with_waveform_visual（布尔值，默认 false）和可为 null 的 waveform_visual（整数数组）。

ElevenCreative

配音

  • 列出配音项目 - GET /v1/dubbing/project
    • page_size 仍为可选整数，默认值为 20，但现在会将值限制在 1–100，而非拒绝请求。
    • status 筛选器现说明 queued、preparing、ready 和 failed。
    • 将上一响应的 next_cursor 传入 cursor；获取第一页时省略该参数。
  • 列出语言目标 - GET /v1/dubbing/project/{project_id}/language
    • page_size 仍为可选整数，默认值为 20，但现在会将值限制在 1–100，而非拒绝请求。
    • status 筛选器支持 queued、processing、completed、stale 和 failed。
    • 将上一响应的 next_cursor 传入 cursor；获取第一页时省略该参数。

Schema 变更

工作区

  • PendingSubscriptionSwitchResponseModel.next_tier 新增 grant。