ElevenLabs Launches Flows to Chain Image Video and Audio Models

ElevenCreative

Mar 18, 2026 · Updated Apr 25, 2026

ElevenLabs launched Flows, a node-based canvas inside ElevenCreative for chaining 35+ image, video, voice, and music models into reusable creative pipelines. Batch-execute a flow with swapped inputs — different products, avatars, or voices — to produce campaign variants at scale.

ElevenLabs launched Flows, a node-based visual canvas inside ElevenCreative that connects image generation, video, Text to Speech, lip-sync, sound effects, and music into a single pipeline. The canvas integrates 35+ models — including Veo, Sora, Kling, Wan, Flux, and Seedance — alongside ElevenLabs' full audio stack: TTS v3, voice cloning, lip-sync, and Eleven Music. Flows support non-destructive editing: re-run a single node and only downstream connected steps update.

This turns multi-tool creative production into reusable infrastructure. Teams building performance marketing assets can swap products, avatars, hooks, and voices systematically to generate structured ad variants without rebuilding the pipeline. Creators can also browse and duplicate Flows made by other creators to start from proven templates. API access is planned for a future release.

Flows is available on all paid ElevenLabs plans. Browse the community Flow library inside ElevenCreative to find ready-made pipelines for ad creative, product imagery, or AI filmmaking.

View the full update on elevenlabs.io

ElevenCreative

@ElevenCreativeMar 11

Introducing Flows in ElevenCreative. Our node-based canvas for exploring and generating with the best image, video, voice, music and SFX models. Experiment with models, chain them together and batch execute - all from one place. https://t.co/3nur4YxRGp

123

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Keep reading

ElevenLabs Flows Agent Builds Multimodal Creative Workflows from Natural Language

ElevenLabs introduced the Flows Agent in its ElevenCreative platform, enabling users to describe a creative project and have the AI autonomously build and execute the entire multi-model workflow. This allows creators and marketers to generate multimodal content through natural language commands and iterative feedback.

HiggsfieldApr 30

Higgsfield Launches Canvas to Chain Frontier Video and Image Models

Higgsfield launched Canvas, a node-based workspace that lets teams build repeatable AI media pipelines by connecting prompts and models on an infinite board. It moves generative AI from isolated chat interactions to collaborative production lines where outputs from one model can automatically trigger the next.

Google DeepMindMay 20

Google Flow Adds Agentic Editing and Character Consistency via Gemini Omni

Google updated its Flow creative studios with Gemini Omni Flash to enable precise video editing and stable character identities across scenes. By introducing an autonomous agent for batch editing and natural language tool creation, Google is shifting AI video from single-clip generation to a managed production workflow.

OpenRouterApr 15

OpenRouter Launches Unified Video Generation API for Multimodal AI Workflows

OpenRouter has launched a unified video generation API that provides access to leading video models through a single integration. This update allows developers to build complex multimodal pipelines where text and image models feed directly into video production.