# ElevenLabs updates Every ElevenLabs update in one feed — release notes, features and changes, straight from the source. 104 updates - ## [ElevenLabs SFX v3 builds richer sound from one prompt]() The new sound-effects model is in ElevenCreative and the API, with stronger multi-sound prompts, music, and vocals. The post does not list a price. 2026-10-29 - ## [Fast LLM service tier]() ElevenAgents can switch supported LLMs to a fast tier for lower latency at a higher per-token price, and the usage calculator now estimates the cost. 2026-10-26 - ## [Knowledge base crawl exclusions]() Website crawls for ElevenAgents knowledge bases accept up to 50 exclude patterns, set through the API or the whole-website crawl dialog. 2026-10-26 - ## [Clone strength for v4 voices]() The new 0 to 1 setting for v4 Professional Voice Clones replaces the deprecated use\_pvc\_as\_ivc flag on Text to Dialogue requests. 2026-10-26 - ## [Expiring service account API keys]() Service account keys in multi-seat ElevenLabs workspaces can expire after 15 minutes to 90 days, set by API field or dashboard. 2026-10-26 - ## [ElevenLabs opens an alpha of live voice translation for calls]() Eleven Realtime Translation lets two people each speak their own language on a call, in 90+ languages. The alpha is limited to enterprise customers. 2026-10-21 - ## [ElevenLabs launches Eleven Realtime speech-to-speech models for voice agents]() Eleven Realtime v1 Mini and v1 Max each work as a complete voice agent, starting to talk in about half a second in 90+ languages. 2026-10-20 - ## [Eleven Realtime: Eleven Realtime is a new family of models for ElevenAgents voice agents]() Two models, Mini and Max, bundle the LLM, speech-to-text and text-to-speech settings for ElevenAgents, with an OpenAI Realtime-compatible API. 2026-10-19 - ## [Realtime Translation: Realtime Translation turns speech in one language into speech in another while the…]() Enterprise workspaces can stream speech through a WebSocket API and get translated speech back in a chosen voice, with optional Zero Retention Mode. 2026-10-19 - ## [Video to Music]() The new API scores up to 10 videos (200 MB combined) as one, with optional sound effects and separate music and SFX tracks. 2026-10-19 - ## [ElevenAgents: Alerts: Alerts notify a workspace when agent error rates exceed a threshold or rise…]() Workspace admins can tune error-rate thresholds per agent and route alerts to webhooks, Slack or PagerDuty, with default monitors running automatically. 2026-10-19 - ## [Music and Sound Effects]() Enterprise customers can set enable\_logging=false on music and sound effects API calls, and Sound Effects can now return WAV audio. 2026-10-19 - ## [Speech Engine: 40-minute conversations: Speech Engine supports conversations of up to 40 minutes]() Speech Engine conversations can now run to 40 minutes, up from the 10-minute default, and the list endpoint can sort by last update. 2026-10-19 - ## [Dubbing: Subtitles for dubbed languages: Dubbing project language outputs (GET…]() The dubbing language endpoint now returns a WebVTT subtitle URL for each dubbed language, signed and valid for one hour. 2026-10-19 - ## [Voices: Resubmittable voice reviews: Voice sharing review\_status adds declined\_resubmittable for…]() A new declined\_resubmittable value in voice sharing's review\_status marks declined voices that can be sent back for another review. 2026-10-19 - ## [Workspaces: Disable service account API keys: Disable service account API key disables a service…]() Workspace admins can switch off a service account key through the API, including after a plan downgrade, and group listings now show concurrency limits. 2026-10-19 - ## [SDK releases: JavaScript SDK v2.74.0 - Added client.conversationalAi.realtime.createClientSecret for…]() The @elevenlabs/client 1.28.0 release adds an experimental persistentSession option and an onConversationHistory callback for resuming WebSocket text chats. 2026-10-19 - ## [ElevenAgents: Merge and search triage tickets: Merge tickets folds up to 50 open tickets from the same…]() Merging moves conversations onto the target ticket and raises its priority to the highest among the merged tickets. 2026-10-12 - ## [Voices: Voice collections API: Voice collections can now be managed through the API]() The listing endpoint returns collections the caller can access, sorted by title and including permission details. 2026-10-12 - ## [Workspaces: Basic seat fallback: Update member accepts allow\_downgrade\_to\_basic\_seat]() Workspace administrators must enable the fallback, which defaults to false and requires an available basic seat. 2026-10-12 - ## [SDK releases: JavaScript SDK v2.72.0 - Added clients for voice collections]() Python gains iterable audio playback, while Scribe adds document context and conversation widgets gain carousels and end confirmation. 2026-10-12 - ## [ElevenAgents Architect drafts and tests agent changes]() The Alpha analyzes agent conversations, proposes versioned changes and creates simulations, with approval required before deployment. 2026-10-06 - ## [ElevenAgents: Structured procedures compile on save and publish]() Integrations can drop separate compile calls, while invalid procedures return per-procedure errors. 2026-10-05 - ## [SDK releases: JavaScript SDK v2.71.0 - Added clients for agent merge proposals, deployment history]() Python gets the same agent clients, while realtime packages add transcript editing and Swift preserves JSON types in dynamic variables. 2026-10-05 - ## [Eleven v4 and Eleven v4 Turbo]() The two models cover 90+ languages, and cloned voices now speak other languages without carrying over their original accent. 2026-09-28 - ## [ElevenAgents: Agent models: Added gpt-6-sol, gpt-6-luna, glm-52, deepseek-v41-flash]() Agent builders can now pick from six new LLMs, and test runs can report credits and USD cost. 2026-09-28 - ## [Flows: Template API: Added endpoints to list and retrieve published Flows templates]() The API lists published Flows templates, starts runs on a chosen version and can post each run's final result to a webhook. 2026-09-28 - ## [Text to Dialogue]() Text to Dialogue API requests can now carry context and request IDs between generations, and use the Instant Voice Clone version of a Professional Voice Clone. 2026-09-28 - ## [SDK releases: JavaScript SDK v2.70.0 - Added batch and realtime Speech to Text transcript editing…]() The JavaScript and Python SDKs both reach v2.70.0 with transcript editing types, and the CLI fixes an API key and OAuth credential conflict. 2026-09-28 - ## [Image & Video]() OpenAI's Sora API retires on 24 September and ByteDance drops Seedance 1.5 Pro on 11 November, so affected flows need a new video model. 2026-09-23 [Open ElevenLabs updates on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/updates/elevenlabs