Sep 1 – Oct 1, 2026 · 5 items
The AI week, for a designer
A real edition, written for: Designer
The one thing
Which of these could cut the most time from your next campaign asset iteration?
Eleven v4 adds voice cloning in 10 seconds
ElevenLabs released Eleven v4 and Eleven v4 Turbo text-to-speech models. Eleven v4 uses a new architecture for more emotive, controllable speech. It supports 90+ languages and 17,500+ voices. Professional Voice Clones are supported again after being absent in v3. Audio tags like laughs or whispers are followed more reliably. Context stitching keeps long-form audio consistent. Regenerations retain the same speaker identity. Eleven v4 Turbo is a low-latency variant for real-time use. It has ~100 ms median inference latency and ~150 ms time to first speech. Both models are available via apps, API, and agents. They support bidirectional streaming for agent loops. Professional Voice Clones work identically across both models. The models are available now.
Why it matters for you
Your campaign voiceovers can now clone a brand voice from a short clip. That cuts the time to match a client’s tone.
- 10-second audio is enough to clone a voice for consistent brand assets
- 90 languages supported means one voice can cover global variants
- Lower latency helps real-time agent demos for client reviews
Try this
Test cloning a brand voice from a 10-second sample and compare it to your current process
Paste this into your AI tool
Context: I need a consistent brand voice for campaign assets Task: clone this voice from the audio I paste I'll paste: [10-second audio clip of the brand voice] Output: the cloned voice ID and a 30-second sample using it
Eleven v4 Turbo cuts latency to ~100ms
ElevenLabs launched v4 and v4 Turbo speech models. They add more expression control and support for 90 languages. Voice cloning now needs only 10 seconds of audio. The model handles voice identity better over long text. It uses inline tags to define and stack expressions. Latency is lower for voice agents. Audio generation starts as soon as the LLM begins answering. The model improves handling of confrontations and escalations. Japanese, Brazilian Portuguese, Mandarin and Cantonese saw the biggest quality gains.
Why it matters for you
Real-time voice previews for client feedback just got practical. That speeds up iteration on audio assets.
- ~100ms latency means near-instant playback for live reviews
- Stacked expression tags let you tweak tone without re-recording
- Works in agents so you can demo interactive voice flows
Try this
Run a live voice preview with v4 Turbo and note the latency vs your current tool
Paste this into your AI tool
Context: I’m testing real-time voice generation for client feedback Task: generate this script with v4 Turbo and time the first word Script: [paste the 20-word script] Output: the audio file and the latency in milliseconds
Manus 2.0 adds video editing with AI
Manus launched Manus 2.0 with a new agent harness called Cascade. Cascade reduces token use, task time and cost versus the prior system. Cloud Computer offers dedicated environments for projects needing persistent hosting. Automations now start from external service events as well as schedules. Manus Studio replaces the desktop app as a shared workspace for people and AI. Studio adds Video Editor for timeline-based video editing and fine-tuning. Video Editor includes Alchemy mode for higher-quality creative direction. Game Dev enables building, editing and publishing multiplayer games. Game Dev supports one-click multiplayer setup via Cloud Computer. Remote Control and Computer Use let users command their computer from elsewhere. Cue is a new standalone app for personal agents on phone and desktop. Cue agents can have their own email, phone, wallet and computer. Cue agents can work in group chats to hand tasks to each other.
Why it matters for you
Your campaign videos can now be edited on a timeline with AI assistance. That shortens the loop from concept to final cut.
- Video Editor with Alchemy mode improves creative direction quality
- Cloud Computer offers dedicated environments for persistent projects
- Remote Control lets you tweak edits from anywhere
Try this
Try Alchemy mode on a rough cut and compare the output to your usual workflow
Paste this into your AI tool
Context: I’m editing a campaign video and want higher-quality creative direction Task: apply Alchemy mode to this rough cut I'll paste: [link to the video file or describe the scene] Output: the edited version with notes on what changed
Sources
Dots run 24/7 on tasks without direction
OpenAI launched Dots, always-on AI assistants that work without constant direction. They run on GPT-6 Astra with their own cloud computer. Dots connect to over 4,000 apps via plugins. They learn user preferences and work 24/7 on tasks. Users can inspect a dot’s work on its cloud computer. Dots can also use a user’s laptop with permission. They message progress or questions in ChatGPT, Slack, or Teams. Built-in safeguards include read-only tools for background work. Users control access, permissions, and approvals via Custom Rules. Specialist dots for organizations have their own identity and access. These are in focused enterprise pilots. Microsoft Agent 365 will integrate specialist dots. Dots roll out to Pro and Business Premium users in eligible markets.
Why it matters for you
Background tasks like resizing assets or batch-exporting variants can now run unattended. That frees you for higher-value work.
- Dots connect to 4,000+ apps so they can handle your usual design tools
- They message progress in Slack or Teams so you stay in the loop
- Pro or Business Premium plans get access first
Try this
Set a Dot to batch-export your latest campaign assets and check the results
Paste this into your AI tool
Context: I need to batch-export campaign assets in multiple formats Task: create a Dot that watches a folder and exports new files to PNG, JPG, and WebP Folder: [paste the folder path] Output: the Dot’s setup steps and a test run on one file
Sources
Perplexity Automations trigger on events
Perplexity Computer launched Automations for long-running agents. Agents remember prior work and pick up where they left off. They run on a schedule or when events occur in Slack, Gmail, Outlook, Linear, or GitHub. Users set triggers, define tasks, and specify outputs like Slack or Gmail. Automations can flag missed updates or deadlines. Users create them via the omnibar or the Automations interface. Admins can limit connector permissions. Automations do not use credits while waiting for triggers. Existing Scheduled Tasks can be migrated to Automations. Automations are available to all Computer users.
Why it matters for you
Your design workflows can now start from a Slack message or GitHub push. That automates the hand-offs that slow you down.
- Agents remember prior work so they pick up where they left off
- No credit cost while waiting for triggers
- Admins can limit connector permissions for security
Try this
Build an Automation that starts a design review when a new asset is pushed to GitHub
Paste this into your AI tool
Context: I want to automate design reviews when new assets are pushed Task: create an Automation that triggers on a GitHub push to [repo name] Action: open a Slack thread with the asset and a review checklist Output: the Automation’s trigger and action configuration
Build this
Every week, one small thing to build with AI in something you actually care about. No work in it. Five minutes to set up, and worth keeping if it earns a second run.
A ranked shortlist of three fonts for your next project, with the last one argued as the best.
Five minutes to set up
Context: I’m choosing a font for a new brand identity Task: rank these three fonts by suitability Fonts: [font 1], [font 2], [font 3] Output: the ranking from best to worst
- Paste the three fonts and run the prompt to get a ranked list
- Ask it to argue why the worst-ranked font is actually the best choice
- Rewrite the ranking based on that argument
- Save the final list and the strongest counter-argument
Yours arrives Thursday.
This one was written for a designer. Tell us what you do and the next one is written for you — same news, your job, once a week.