ElevenLabs announced Chimera on October 21, a workflow template inside its ElevenCreative platform that combines voice generation and video synthesis into a single production step. Users upload a character image, write dialogue, and select or design a voice. Chimera renders a video of that character speaking the lines.
The feature ties together two models that creators were already using in sequence. Eleven v4, which ElevenLabs released on September 28, handles the speech synthesis. ByteDance's Seedance 2.5, available through ElevenCreative since July, generates the video and synchronizes lip movement to the audio track.
What if your character could finally say it themselves? With Chimera they can. Chimera pairs two of the world’s leading models, Eleven v4 and Seedance 2.5, to create realistic video with rich, emotional voices. In ElevenCreative, create or upload a character, write their line, and pick a voice or design one to match. Direct the performance with audio tags like [whispers], [laughs] and [yells] to control the timing and mood of every word. Eleven v4 puts the emotion in the voice. Seedance 2.5 carries it onto the face.
— ElevenCreative (@ElevenCreative) October 21, 2026
How the Pieces Fit
Eleven v4 is the company's newest text-to-speech engine. It supports inline performance tags that let users control timing and emotion through notation in the script. Markers like [whispers], [laughs], and [yells] direct how lines are delivered.
"Eleven v4 is built on a new architecture with more emotional range and granular control," CTO Piotr Dąbkowski said at the model's launch. "The model has a deep understanding of audio and prosody, so it produces richer performances and more natural dialogue between speakers."
Seedance 2.5 generates video clips up to 30 seconds long in a single pass and accepts up to 50 multimodal reference inputs: images, audio, and video. The model was ByteDance's response to the short clip lengths that have constrained most AI video generators. It supports lip synchronization across 20 languages and can match facial motion to the audio it receives.
A Template, Not a Model
Chimera is not a new model. It is a pre-built template in ElevenCreative's Flows system, which chains generation steps together so users do not have to export and import files between tools manually. The same voice and video models remain available individually for users who want finer control or different configurations.
ElevenLabs has been building out ElevenCreative since March, adding video models from multiple providers alongside its core voice technology. The platform now offers image generation, video generation, dubbing, music, and sound effects.
A Complication for US Users
There is a catch. Seedance 2.5 remains unavailable to users in the United States through most channels, including ElevenLabs. The model comes from ByteDance, the same company behind TikTok, and carries the same regulatory ambiguity. ByteDance launched Seedance 2.5 in July through its own apps for users in Southeast Asia, Europe, the Middle East, Africa, and South America. The US was excluded from that rollout and has not been added since.
ElevenLabs' documentation states that Seedance 2.5 Video Edit, a related model, is "from a China-based provider and is not currently available to ElevenLabs users in the United States." Whether the base Seedance 2.5 model used by Chimera carries the same restriction is not spelled out on the template page, but the underlying geopolitical constraints have not changed.
Third-party platforms have begun offering Seedance 2.5 access without the regional block, but running the model through ElevenCreative's Chimera template specifically appears to depend on ElevenLabs' own implementation.
What Chimera Costs
ElevenLabs has not published separate pricing for Chimera. The company charges for voice generation by character count and for video generation by output length. Both models remain available at standard rates. API pricing for Eleven v4 lists at $0.08 per 1,000 characters, with a $0.04 rate for the low-latency Turbo variant. Seedance 2.5 video costs vary by resolution and length.
The Chimera template is live in ElevenCreative now for users in supported regions.
