# Unifically

> API documentation for Unifically — a unified API for image, video, and audio AI models.

## Docs

- [Account Information](https://docs.unifically.com/api-reference/account-information.md): Retrieve your account information and usage statistics
- [Authentication](https://docs.unifically.com/api-reference/authentication.md): Learn how to authenticate your API requests
- [Webhooks & Callbacks](https://docs.unifically.com/api-reference/callbacks.md): Receive task completion notifications via webhook callbacks
- [Error Handling](https://docs.unifically.com/api-reference/error-handling.md): Understanding Unifically API error responses
- [Resources](https://docs.unifically.com/api-reference/resources.md): Get provider resources like motions, voices, and sounds
- [Base64 Upload](https://docs.unifically.com/api-reference/storage/base64-upload.md): Upload files as base64-encoded strings
- [Direct File Upload](https://docs.unifically.com/api-reference/storage/direct-upload.md): Upload files directly using multipart/form-data
- [Storage Overview](https://docs.unifically.com/api-reference/storage/overview.md): Upload and store files using multiple methods
- [URL Upload](https://docs.unifically.com/api-reference/storage/url-upload.md): Upload files by providing a URL
- [Unified Tasks API](https://docs.unifically.com/api-reference/v1-tasks.md): Create and manage AI generation tasks with a unified interface
- [Introduction](https://docs.unifically.com/introduction.md): Welcome to Unifically - Your unified API for AI Models
- [Sound Effect](https://docs.unifically.com/models/audio/elevenlabs/sound-effect.md): Generate sound effects with ElevenLabs
- [Speech-to-Text](https://docs.unifically.com/models/audio/elevenlabs/speech-to-text.md): Transcribe audio to text with ElevenLabs
- [Text-to-Dialogue](https://docs.unifically.com/models/audio/elevenlabs/text-to-dialogue.md): Generate multi-voice dialogue with ElevenLabs
- [Text-to-Speech](https://docs.unifically.com/models/audio/elevenlabs/text-to-speech.md): Generate speech with ElevenLabs TTS
- [Voice Changer](https://docs.unifically.com/models/audio/elevenlabs/voice-changer.md): Convert voice in audio with ElevenLabs
- [Voice Isolation](https://docs.unifically.com/models/audio/elevenlabs/voice-isolation.md): Isolate vocals from audio with ElevenLabs
- [Add Instrumental](https://docs.unifically.com/models/audio/suno/add-instrumental.md): Add instrumental backing to uploaded music
- [Add Vocals](https://docs.unifically.com/models/audio/suno/add-vocals.md): Add vocals to uploaded music
- [Cover Generation](https://docs.unifically.com/models/audio/suno/cover.md): Create cover versions with Suno AI
- [Extend Music](https://docs.unifically.com/models/audio/suno/extend.md): Extend existing songs with Suno AI
- [Generate Lyrics](https://docs.unifically.com/models/audio/suno/lyrics.md): Generate lyrics with Suno AI
- [Music Generation](https://docs.unifically.com/models/audio/suno/music.md): Generate music with Suno AI
- [Sound Effects](https://docs.unifically.com/models/audio/suno/sound.md): Generate sound effects with Suno AI
- [Extract Stems](https://docs.unifically.com/models/audio/suno/stems.md): Extract vocals and instrumental tracks
- [Voice Creation](https://docs.unifically.com/models/audio/suno/voice.md): Create custom voices with Suno AI
- [WAV Export](https://docs.unifically.com/models/audio/suno/wav.md): Export Suno clips as WAV files
- [Qwen Image](https://docs.unifically.com/models/image/alibaba/qwen-image.md): Base Qwen image model with text-to-image and editing support
- [Qwen Image 2.0](https://docs.unifically.com/models/image/alibaba/qwen-image-2.0.md): Balanced quality and speed image generation with editing support
- [Qwen Image 2.0 Pro](https://docs.unifically.com/models/image/alibaba/qwen-image-2.0-pro.md): Best quality image generation with text rendering and image editing
- [Qwen Image Max](https://docs.unifically.com/models/image/alibaba/qwen-image-max.md): Highest realism image generation with fewest AI artifacts and image editing
- [Qwen Image Plus](https://docs.unifically.com/models/image/alibaba/qwen-image-plus.md): Diverse artistic styles with fast image generation and editing
- [Wan 2.2 Flash](https://docs.unifically.com/models/image/alibaba/wan-2.2-flash-image.md): Fast and affordable text-to-image generation
- [Wan 2.2](https://docs.unifically.com/models/image/alibaba/wan-2.2-image.md): Text-to-image generation with Wan 2.2
- [Wan 2.5](https://docs.unifically.com/models/image/alibaba/wan-2.5-image.md): Image generation with text-to-image and editing support
- [Wan 2.6](https://docs.unifically.com/models/image/alibaba/wan-2.6-image.md): Image generation with style transfer and editing support
- [Wan 2.7](https://docs.unifically.com/models/image/alibaba/wan-2.7-image.md): Fast variant of Wan 2.7 Pro with text-to-image and editing
- [Wan 2.7 Pro](https://docs.unifically.com/models/image/alibaba/wan-2.7-pro-image.md): Highest quality image generation with thinking mode and up to 4K
- [Z-Image Turbo](https://docs.unifically.com/models/image/alibaba/z-image-turbo.md): Lightweight fast text-to-image with text rendering support
- [SeeDream 4.0](https://docs.unifically.com/models/image/bytedance/seedream-4.0.md): Image generation with up to 6 reference images
- [SeeDream 4.1](https://docs.unifically.com/models/image/bytedance/seedream-4.1.md): Image generation with up to 6 reference images and 4K resolution
- [SeeDream 4.5](https://docs.unifically.com/models/image/bytedance/seedream-4.5.md): Image generation with up to 6 reference images and 4K resolution
- [SeeDream 4.6](https://docs.unifically.com/models/image/bytedance/seedream-4.6.md): High-quality image generation with up to 6 reference images and 4K resolution
- [SeeDream 5.0 Lite](https://docs.unifically.com/models/image/bytedance/seedream-5.0-lite.md): Latest lightweight image generation with up to 6 reference images and 4K resolution
- [Flux.2 Flex](https://docs.unifically.com/models/image/flux/flux.2-flex.md): Flexible image generation with advanced controls
- [Flux.2 Klein 4B](https://docs.unifically.com/models/image/flux/flux.2-klein-4b.md): Fastest image generation with Flux.2 Klein 4B
- [Flux.2 Klein 9B](https://docs.unifically.com/models/image/flux/flux.2-klein-9b.md): Lightweight image generation with Flux.2 Klein 9B
- [Flux.2 Max](https://docs.unifically.com/models/image/flux/flux.2-max.md): Maximum quality image generation
- [Flux.2 Pro](https://docs.unifically.com/models/image/flux/flux.2-pro.md): High-quality image generation with Flux.2 Pro
- [Nano Banana](https://docs.unifically.com/models/image/google/nano-banana.md): Fast image generation with Google Gemini 2.5 Flash
- [Nano Banana 2](https://docs.unifically.com/models/image/google/nano-banana-2.md): Next-generation image generation with Google Gemini
- [Nano Banana Pro](https://docs.unifically.com/models/image/google/nano-banana-pro.md): Advanced image generation with Google Gemini 3
- [Kling v2.1 Image](https://docs.unifically.com/models/image/kling/kling-2.1-image.md): Generate images with 4 reference modes: restyle, portrait, character, and elements
- [Kling v3.0 Image](https://docs.unifically.com/models/image/kling/kling-3.0-image.md): Generate high-quality images with batch generation support
- [Kling Omni Image](https://docs.unifically.com/models/image/kling/kling-omni-image.md): Generate high-quality images with reference image support
- [GPT Image 2](https://docs.unifically.com/models/image/openai/gpt-image-2.md): Generate images with OpenAI's GPT Image 2 model
- [Topaz Image Upscale](https://docs.unifically.com/models/image/topaz-labs/image-upscale.md): AI-powered image upscaling with selectable presets, face recovery, and per-preset tuning
- [Grok Imagine Image](https://docs.unifically.com/models/image/xai/grok-imagine-image.md): Generate and edit images with xAI Grok Imagine
- [HappyHorse 1.0](https://docs.unifically.com/models/video/alibaba/happyhorse-1.0-video.md): Video generation with text-to-video, image-to-video, and reference-to-video modes
- [HappyHorse 1.0 Video Edit](https://docs.unifically.com/models/video/alibaba/happyhorse-1.0-video-edit.md): Edit existing videos with optional reference images for style guidance
- [Wan 2.2 Flash](https://docs.unifically.com/models/video/alibaba/wan-2.2-flash-video.md): Fast silent video generation with text-to-video and image-to-video
- [Wan 2.2](https://docs.unifically.com/models/video/alibaba/wan-2.2-video.md): Silent video generation with text-to-video and image-to-video
- [Wan 2.5](https://docs.unifically.com/models/video/alibaba/wan-2.5-video.md): Video generation with audio sync and flexible resolution
- [Wan 2.6 Flash](https://docs.unifically.com/models/video/alibaba/wan-2.6-flash-video.md): Fast video generation with audio, multi-shot, and reference-to-video support
- [Wan 2.6](https://docs.unifically.com/models/video/alibaba/wan-2.6-video.md): Advanced video generation with audio, multi-shot, and reference-to-video support
- [Wan 2.7](https://docs.unifically.com/models/video/alibaba/wan-2.7-video.md): Unified video generation with text-to-video, image-to-video, and reference-to-video modes
- [Wan 2.7 Video Edit](https://docs.unifically.com/models/video/alibaba/wan-2.7-video-edit.md): Edit or style-transfer existing videos with optional reference images
- [SeeDance 1.0 Fast](https://docs.unifically.com/models/video/bytedance/seedance-1.0-fast.md): Fast video generation with multi-frame keyframe support
- [SeeDance 1.0 Mini](https://docs.unifically.com/models/video/bytedance/seedance-1.0-mini.md): Compact video generation with multi-frame keyframe support
- [SeeDance 1.0 Pro](https://docs.unifically.com/models/video/bytedance/seedance-1.0-pro.md): High-quality video generation with first & last frame support
- [SeeDance 1.5 Pro](https://docs.unifically.com/models/video/bytedance/seedance-1.5-pro.md): Professional video generation with first & last frame support up to 1080p
- [SeeDance 2.0 Fast](https://docs.unifically.com/models/video/bytedance/seedance-2.0-fast.md): Fast video generation with omni-reference support
- [SeeDance 2.0 Fast (Low Restriction)](https://docs.unifically.com/models/video/bytedance/seedance-2.0-fast-low-restriction.md): Fast video generation with face usage and reduced moderation
- [SeeDance 2.0 Pro](https://docs.unifically.com/models/video/bytedance/seedance-2.0-pro.md): High-quality video generation with omni-reference support
- [SeeDance 2.0 Pro (Low Restriction)](https://docs.unifically.com/models/video/bytedance/seedance-2.0-pro-low-restriction.md): High-quality video generation with face usage and reduced moderation
- [Gemini Omni Flash Video](https://docs.unifically.com/models/video/google/gemini-omni-flash-video.md): Generate videos with Google's Gemini Omni Flash video model
- [Gemini Omni Flash Video Edit](https://docs.unifically.com/models/video/google/gemini-omni-flash-video-edit.md): Edit videos with Google's Gemini Omni Flash video edit model
- [Veo 3.1](https://docs.unifically.com/models/video/google/veo-3.1.md): Generate videos with Google's Veo 3.1 models
- [Kling v2.1](https://docs.unifically.com/models/video/kling/kling-2.1.md): Generate videos with Kling v2.1 models
- [Kling v2.5 Turbo](https://docs.unifically.com/models/video/kling/kling-2.5.md): Generate videos with Kling v2.5 Turbo
- [Kling v2.6](https://docs.unifically.com/models/video/kling/kling-2.6.md): Generate videos with Kling v2.6 and voice support
- [Kling Motion Control 2.6](https://docs.unifically.com/models/video/kling/kling-2.6-motion-control.md): Transfer motion from reference videos onto characters
- [Kling v3.0](https://docs.unifically.com/models/video/kling/kling-3.0.md): Generate videos with Kling v3.0 and multi-shot support
- [Kling Motion Control 3.0](https://docs.unifically.com/models/video/kling/kling-3.0-motion-control.md): Transfer motion from reference videos onto characters with high facial consistency
- [Kling v3.0 Omni](https://docs.unifically.com/models/video/kling/kling-3.0-omni-video.md): Generate videos with Kling v3.0 Omni
- [Kling v3.0 Omni Video Edit](https://docs.unifically.com/models/video/kling/kling-3.0-omni-video-edit.md): Edit videos with Kling v3.0 Omni
- [Kling O1 Video](https://docs.unifically.com/models/video/kling/kling-o1-video.md): Generate videos with Kling O1
- [Kling O1 Video Edit](https://docs.unifically.com/models/video/kling/kling-o1-video-edit.md): Edit videos with Kling O1
- [Minimax Hailuo](https://docs.unifically.com/models/video/minimax/hailuo.md): Generate videos with Minimax Hailuo models
- [Topaz Video Upscale](https://docs.unifically.com/models/video/topaz-labs/video-upscale.md): AI-powered video upscaling with selectable Topaz models, enhancement tuning, and optional frame interpolation
- [Grok Imagine Upscale](https://docs.unifically.com/models/video/xai/grok-imagine-upscale.md): Upscale a Grok Imagine video to HD
- [Grok Imagine Video](https://docs.unifically.com/models/video/xai/grok-imagine-video.md): Generate videos with xAI Grok Imagine
- [Grok Imagine Video 1.5 Preview](https://docs.unifically.com/models/video/xai/grok-imagine-video-1.5-preview.md): Animate images into video with xAI Grok Imagine 1.5 (preview)
- [Grok Imagine Video Edit](https://docs.unifically.com/models/video/xai/grok-imagine-video-edit.md): Edit videos with xAI Grok Imagine
- [Grok Imagine Video Extend](https://docs.unifically.com/models/video/xai/grok-imagine-video-extend.md): Extend videos with xAI Grok Imagine

## OpenAPI Specs

- [openapi](https://docs.unifically.com/api-reference/openapi.json)

## Optional

- [Website](https://unifically.com)