OneRange

What's New in ElevenLabs

A short refresher on the latest ElevenLabs updates

What this course covers

The course runs across 7 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

  • A more expressive text to speech model — What's different: ElevenLabs released a new speech model that sounds more emotional and natural, follows audio tags like [excited] or [whispers] more closely, works in more than 90 languages, and makes closer voice clones. Why it matters for your work: Voiceovers, training audio and narration can now sound like a real performance, and one voice can speak many languages with a native accent. Try it (about 2 minutes): Open Text to Speech, pick the newest Eleven model in the model menu, type "[excited] Our new menu drops this Friday!" and generate it, then try the same line with [calm] instead. No access? Here's what you'd see: The Text to Speech model menu now displays the newest Eleven model.
  • Studio is now a full video editor with an AI co-editor — What's different: Studio in ElevenCreative was rebuilt so you can generate video, images, voiceover, music and sound effects right on a new timeline, and Studio Agent drafts a first cut from your description. Why it matters for your work: You can make a finished social clip, explainer or product video in one project instead of moving files between several tools. Try it (about 2 minutes): Open Studio, type a short description such as "30-second product teaser with upbeat music and a friendly narrator" in the prompt bar, and let Studio Agent build a first draft you can edit. No access? Here's what you'd see: ElevenCreative Studio displays a new timeline for generating video, images, and audio, alongside a prompt bar for the Studio Agent.
  • Architect helps you build and fix agents by chat — What's different: ElevenAgents now has Architect, a built-in helper you talk or type to, which studies transcripts and test results, suggests changes to an agent and writes tests for them. Why it matters for your work: Teams who run voice agents can find why calls go wrong and improve the agent without being experts in every setting. Try it (about 2 minutes): Open an agent in ElevenAgents, open Architect, and ask "Why are callers asking for a human so often?" Then review the change it suggests before you accept it.
  • Add matching music and sound effects to any video — What's different: Instant Soundtracks in ElevenCreative scores an uploaded video with original music and places matching sound effects on the timeline, and can use the video's own audio as a style reference. Why it matters for your work: Social clips and ads get a fitting soundtrack in minutes, and the effects sit on their own layer so you can adjust them. Try it (about 2 minutes): In ElevenCreative, open the Music section, upload a short video in the Music Video Editor, generate a soundtrack with sound effects, then move or delete one effect on its layer. No access? Here's what you'd see: In ElevenCreative's Music section, the Music Video Editor displays generated soundtracks and matching sound effects on their own layer.
  • Use ElevenLabs from inside Claude, ChatGPT and more — What's different: The hosted ElevenLabs connector lets AI assistants such as Claude and ChatGPT create speech, transcripts, dubs, music, sound effects, images and video, and manage your agents, after one sign-in. Why it matters for your work: You can ask for a voiceover or a transcript in the assistant you already use, and the result is saved to your ElevenCreative workspace. Try it (about 2 minutes): In your AI assistant, add the ElevenLabs connector from its connector list, sign in with your ElevenLabs account, and ask it to "make a 10-second voiceover saying welcome to the team." No access? Here's what you'd see: The ElevenLabs connector appears in the connector list of AI assistants like Claude and ChatGPT.
  • Also new — - Sora video models removed from Image & Video: OpenAI's Sora 2 and Sora 2 Pro models were removed from Image & Video. - Realtime models make agent setup simpler: Eleven Realtime, a new family of all-in-one voice agent models, has launched. - Expressive real-time voices for agents: A low-delay version of the new speech model is now available in ElevenAgents. - Procedures give one agent many task playbooks: Procedures are now fully released in ElevenAgents to manage multi-step tasks. - Agent alerts, and guardrails are fully released: ElevenAgents now sends alerts for error rates and has fully released Guardrails. - Brand Kit keeps images and videos on brand: Brand Kit in ElevenCreative stores brand assets to keep generated visuals consistent. - Character Casting picks voices for audiobook roles: Character Casting in Audiobooks automatically identifies roles and suggests voices. - Agent Triage is now called Issues: The Triage area in the ElevenAgents dashboard has been renamed to Issues. - Slack, Telegram and Intercom agent channels leave alpha: Slack, Telegram, Intercom, and Custom Channel integrations have left alpha. - A better default music model: A new music model is now the default in ElevenMusic and ElevenCreative. - and 5 more: Procedures analytics open to all workspaces; Skip pages when an agent crawls your website; Agents can tell human callers from AI voices; Editable project-based dubbing in the API; Parallel tool calling switch removed for Realtime
  • Try one on your own work — Pick the one main change from this course that is most useful to your job. Try it in your own ElevenLabs on a real task, then paste or describe what you got. The coach gives short, specific feedback. No access to the app or plan it needs? Describe how you would use it on a real task this week. That counts too. There is no score and no pass or fail: finishing this completes the course.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

The material is pitched at intermediate level, and takes roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: ElevenLabs track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

  • ElevenLabs & AI Voice — Learners generate natural voiceover and audio with AI voice tools like ElevenLabs. The course covers text-to-speech, the ethics of voice cloning, dubbing, quality, and use cases. Participants finish able to add professional audio to their content responsibly.

Related

Frequently asked questions

How long does this course take?

It runs roughly 20 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code what-s-new-in-elevenlabs-ee908cee.