#does elevenlabs do image generatoion
1 messages · Page 1 of 1 (latest)
No. ElevenLabs does not offer an image-generation model or API; its products focus on AI audio (text-to-speech/voice cloning and changer, speech-to-text, dubbing/agents), sound‑effect generation, and Eleven Music. (elevenlabs.io)
Some ElevenLabs demos and partner posts show voice-driven image creation, but the visuals come from third‑party image models (e.g., FLUX Kontext in “Vibe Draw” or Hedra’s Character‑1), not from ElevenLabs itself. (elevenlabs.io)
Sources:
Free AI Voice Generator & Voice Agents Platform | ElevenLabs
ElevenLabs & FLUX Kontext: voice-powered image creation
Bot probably needs updating but yes, from today
Confirmed. As of November 6, 2025, ElevenLabs offers Image & Video (beta) for text-to-image and text-to-video creation. Capabilities include image generation from prompts or references, video generation with integrated audio, iterative refinement, 4x upscaling, lip‑sync from audio, and exports to PNG (images) and MP4 H.264/H.265 (videos; up to 4K with upscaling). (elevenlabs.io)
Available models include, for video: OpenAI Sora 2 Pro/Sora 2, Google Veo 3.1/3.1 Fast/3/3 Fast, Kling 2.5, Seedance 1 Pro, Wan 2.5; and for images: Google Nano Banana, Seedream 4, Flux 1 Kontext Pro, Wan 2.5, OpenAI GPT Image 1. Pricing varies by model (e.g., Sora 2 Pro starts at 12,000 credits per generation). See the docs for details. (elevenlabs.io)
Sources:
Image & Video | ElevenLabs Documentation
Image & Video | ElevenLabs Documentation
well well well @urban arch
I don’t see a specific ElevenLabs question here. Could you clarify what you need help with (e.g., Text-to-Speech API, Voice Library/Design, real‑time, dubbing, billing, rate limits, SDKs, webhooks, errors)? If it’s an API issue, please include:
- endpoint and SDK/language
- request/response snippets (redact keys)
- error message and request ID
- expected vs. actual behavior
did you see the announcement today?