AI Creative Models: Images, Video & Music | SnapGen

Explore image, video, music and audio models. Connect Claude, Codex or ChatGPT for supported creative tasks, or try available models in the Playground.
The newest model families on SnapGen, freshest first.
Create and edit images with Seedream 5.5. Use up to ten reference images and choose 1K, 1.5K or 2K output.
Create videos with native sound from text, images, first and last frames, or subject references.
Create 3–30 second Kling 4.0 AI videos from text, start and end frames or image references. Explore native stereo audio, resolutions and current prices.
Create Meta Muse Video clips from text or reference images. Explore about 10-second 720p videos with native sound, supported inputs and current prices.
Create and edit 1K images with GPT Image 2.6 Flare or Sunburst. Compare quality choices, up to 16 references, supported settings and per-image prices.
Create Gemini Omni AI videos with native audio from text, images or references. Compare 720p and 1080p options, supported modes and current prices.
Create 4–10 second Gemini Omni Flash 1.1 videos with native audio. Explore text, frame and reference inputs, clip extension, resolutions and prices.
Create 4–15 second MiniMax H3, also known as Hailuo 03, videos with native stereo audio. Compare six aspect ratios, 768P and 2K settings and prices.
Create 4–15 second Seedance 2.0 AI videos with native audio. Compare text, image and reference modes, resolutions from 480p to 4K, and current prices.
Create Seedance 2 Fast video drafts from text, images or references. Choose 4–15 seconds at 480p or 720p and compare audio settings and live prices.
Explore Seedance 2 Mini for 4–15 second AI videos from text, images or references. Compare 480p and 720p, optional audio and current generation costs.
Create 4–30 second Seedance 2.5 videos with optional audio. Compare generation, reference, editing and extension modes and check each model’s price.
Create 6–30 second Grok Imagine 1.5 videos from a prompt with up to seven optional reference images. Compare 480p, 720p and current generation prices.
Generate fixed 8-second Veo 3.1 videos with synchronized native audio. Explore 1080p and 4K, start and end frames, model options and current prices.
Create and edit Nano Banana 2.1 images at 1K, 2K or 4K. Explore reference images, aspect ratios, supported inputs and current per-image prices.
Generate and edit images with GPT Image 2.5 Ext Flare or Sunburst. Explore 1K, 2K and 4K, up to 16 reference images, settings and current prices.
Create AI images with GPT Image 2. Compare low, medium and high quality, square, portrait and landscape sizes, available settings and current prices.
Explore Suno V6 for songs with vocals or your own lyrics. Compare generation, cover, extension and stem operations, supported settings and current prices.
Create songs with Flow Music on Google Lyria 3 Pro and 3.5. Explore prompts, lyrics, extensions, covers, stems and MP3 or WAV outputs with current pricing.
Turn text into speech with Eleven v4, v3, Multilingual v2 or Flash v2.5. Compare voices, dialogue settings and per-character prices in the Playground.
Use GPT-6 Luna, Sol and Astra, plus GPT-6.1 Sol, with one SnapGen key and prepaid balance.
Flux 3 is an upcoming Black Forest Labs multimodal model. Check announced capabilities; confirmed availability, supported settings and prices will follow.
Transcribe audio and video in 90+ languages with ElevenLabs Scribe v2. Explore speaker labels, word timestamps, SRT subtitles and forced alignment.
Compose music with Eleven Music v2.5 from a prompt, optional lyrics or an instrumental brief. Compare duration, audio formats and current per-second prices.
Create foley, ambience and seamless loops from a text description with ElevenLabs Sound Effects v2. Check duration, audio formats and current prices.
Change a recording’s voice while preserving its timing and emotion, or isolate speech from background noise. Compare voices, supported inputs and prices.
Translate and dub video or audio into 32 languages with ElevenLabs Dubbing. Keep speakers distinct, check source-duration costs and follow the task to download.
Call GPT-5.6 Luna, Terra and Sol through OpenAI-compatible Chat Completions and Responses.
Anthropic Claude text models are coming soon to this catalog. For image and video creation in the Claude assistant, use the account connection guide.
Use the Gemini text models currently available through the SnapGen chat gateway.
xAI Grok 4.6, 4.5 and 4.3 through the OpenAI-compatible Chat Completions and Responses APIs, with streaming, reasoning, and cached-input pricing at the xAI list rate.
Use the DeepSeek models currently available through the SnapGen chat gateway.
Qwen text models are coming soon to this catalog. Confirmed model availability, request formats and prices will appear when production access is enabled.
Every model below works with the same SnapGen key and prepaid balance.
Create images, videos, music and dubbed clips with Claude, Codex or ChatGPT. One account, pay as you create.