Start free

AI models

AI Models

Generate video, images, voice and music with AI models inside your Shotstack renders.

Start Free Docs

Text to video

Generate a video clip from a prompt and edit it into your timeline in the same render.

  • ByteDance

    Seedance 2.0

    Generate cinematic video with realistic motion, prompt-directed camera movement and optional synchronised audio.

  • ByteDance

    Seedance 2.5

    Generate video up to 30 seconds long with optional synchronised audio. Supports longer scenes in a single generation.

  • Alibaba

    Wan 3.0 Prime

    Generate video from a prompt for up to 30 seconds with optional audio.

  • Google

    Gemini Omni Flash 1.1

    Generate video from a prompt for 3–10 seconds with native audio, at resolutions up to 4K.

Image to video

Animate a still image into a video clip, with optional audio on some models.

  • ByteDance

    Seedance 2.0

    Animate a still image with realistic motion, prompt-directed camera movement and optional synchronised audio. Supply an ending image to guide the final frame.

  • ByteDance

    Seedance 2.5

    Animate a still image into video up to 30 seconds long, with optional synchronised audio and an ending image to guide the final frame.

  • Alibaba

    Wan 3.0 Prime

    Animate an image for up to 30 seconds with optional audio.

  • Google

    Gemini Omni Flash 1.1

    Animate an image for 3–10 seconds with native audio, at resolutions up to 4K.

Text to image

Generate images from a prompt, from quick drafts to detailed product and campaign visuals.

  • Google

    Nano Banana 2

    Generate images quickly with accurate text and coherent compositions. Suited to rapid iteration, product visuals and campaign assets.

  • Google

    Nano Banana Pro

    Generate images with complex compositions and precise typography. Prioritises detail and prompt understanding over speed.

  • OpenAI

    GPT Image 2.5 Sunburst

    Generate highly detailed images that follow complex prompts closely. Slower than other image models; suited to final creative and product imagery.

  • Black Forest Labs

    FLUX Schnell

    Generate images from text prompts for illustrations and visual drafts.

Image to image

Edit existing images with instructions and reference images.

  • Google

    Nano Banana 2

    Edit images with natural-language instructions and up to 14 references. Suited to product retouching, style changes and combining images.

  • OpenAI

    GPT Image 2.5 Sunburst

    Edit images with precise instructions and up to 16 ordered references. Describe what to change and what to preserve.

Text to speech

Turn a script into a voiceover, in a choice of voices and languages.

  • ElevenLabs

    ElevenLabs Multilingual v2

    Generate natural, consistent speech across 29 languages. Suited to narration, educational content and localisation.

  • ElevenLabs

    ElevenLabs Turbo v2.5

    Generate natural-sounding speech quickly across 32 languages. Optimised for low latency.

  • MiniMax

    MiniMax Speech 2.8 HD

    Turn text into speech using a choice of voices and languages. Useful for narrated videos and spoken stories.

  • Amazon

    Amazon Polly Neural

    Turn text into natural-sounding speech. Useful for straightforward narration, explainers and news-style voiceovers.

Music

Generate a music track from a prompt, with vocals or instruments only.

  • ElevenLabs

    ElevenLabs Music

    Create music from a prompt, with vocals or instruments only. Useful for background tracks or songs with planned sections and lyrics.

Questions

Do I need an account with the model provider?
No. Generation runs on your Shotstack API key and is paid in credits from the same balance as rendering, so there is no separate account to open and nothing extra to integrate.
Do I pay again for the same asset?
No. Every generated file is stored against your account. An asset with the same type, model, prompt, options and length as one generated before reuses the stored file at no charge.
What happens if a generation fails?
A failed generation isn't charged. If a render fails after some of its assets were generated, those assets are kept, and rendering again reuses them at no charge.
Can I generate an asset without rendering a video?
Yes. POST the asset to the generate endpoint and you get back a URL to the file, to check it before you render, to reuse it across many edits, or to use it outside Shotstack.

Start free

  • 10 free credits to start
  • No credit card required
Start Free All integrations