Adds AI-generated sound effects, foley and ambience to a silent video, synchronized to the visual content. Describe the desired sound in the prompt.

inclusionAI Ling 3.1 Flash: fast hybrid-reasoning mixture-of-experts model (560B total, 25B active) with a 1M-token context. Served via OpenRouter.

NVIDIA Nemotron 3.5 Super VL: 120B mixture-of-experts vision-language model (12B active) with a 1M-token context and image and video input. Served via OpenRout…

Z.ai's top-tier GLM-5.3 Prime: 1M-token context, built for long-horizon coding and agent work. Served via OpenRouter.

MiniMax M3.1 Flash: fast multimodal model with 1M-token context, strong at agentic tasks and coding. Served via OpenRouter.

Moonshot AI's Kimi K3.1 Pro: open-weight multimodal reasoning model for long-horizon coding, 1M-token context. Served via OpenRouter.

OpenAI's GPT-6.1 Terra Pro: GPT-6.1 Terra served in pro reasoning mode for harder tasks, 1.05M-token context. Served via OpenRouter.

OpenAI's GPT-6.1 Terra: the mid-tier model of the GPT-6.1 series with 1.05M-token context. Served via OpenRouter.

StepFun's flagship model for agentic work: sparse Mixture-of-Experts (27B active / 600B total), strong at software engineering and professional tasks, 1M-token…

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated…

Cohere's Command A+: enterprise model for agentic, RAG and multilingual workloads with 192K-token context. Served via OpenRouter.

Meta's Muse Spark Open: open-weights Muse Spark variant with 1M-token context. Served via OpenRouter.

Meta's Muse Wonder: large Muse reasoning model with 1M-token context. Served via OpenRouter.

OpenAI's GPT-6.1 Sol Pro: the Pro tier of GPT-6.1 Sol with 1.05M-token context. Served via OpenRouter.

Google's Gemini 4 Argon: reasoning model with 1M-token context and multimodal input. Served via OpenRouter.

Inkling — frontier text model from Thinking Machines Lab with a 524k context window.

DeepSeek V4.1 Flash — fast, low-cost 1M-context text model from DeepSeek.

MiniMax M3 — long-context (1M) frontier text model from MiniMax.

A lower-cost variant of Seedance 2.0 for high-volume video generation with multimodal inputs and native audio.

Generate video with synchronized audio from text, images, or video. FLUX 3 is Black Forest Labs' multimodal model (early access preview).

FLUX 3 is Black Forest Labs' text-to-image and image-editing model. Generate images from a prompt, or edit with up to 10 reference images.

Generate and edit images with Ideogram 4.5, the latest for precise image generation.

Foundation image model from Krea, tuned for expressive illustration, anime, and painterly styles. Fast and consistent across artistic directions.

Mistral's new flagship model with a 1M-token context window.

GPT-6.1 Sol from OpenAI — a flagship general-purpose model with a 1M-token context window.

Claude Haiku 5.5 from Anthropic — the fastest and most affordable Claude, built for high-volume everyday tasks.

Claude Sonnet 5.5 from Anthropic — a fast, capable all-round model for writing, coding and analysis with a 1M-token context window.

Google's fastest image generation model — the lightweight, low-cost version of Nano Banana 2, for rapid creation and editing

Google's latest fast image generation model with sharp text rendering, conversational editing, multi-image fusion, and up to 4K output

Qwen3.8 Omni Flash is Alibaba's first Qwen model built around agentic capabilities with native omni-modal audio-video understanding, 1M context, and tool use.

GPT-6 Luna is OpenAI's budget tier in the GPT-6 family, recently price-cut to $0.10/$0.50 per million tokens.

OpenAI's GPT-6 mid tier — successor to GPT-5.6 Sol, at OpenAI's current post-price-cut rate.

OpenAI's GPT-6 flagship model, a new generation above the GPT-5.6 family.

xAI's current flagship coding and knowledge model, GA September 2026, with text + image input and a 500K token context window.

Anthropic's most capable widely released model — successor to Claude Fable 5, for the most demanding reasoning and long-horizon agentic work, with a 1M token c…

Anthropic's Opus 5.5 — beats Fable 5.1 on agentic benchmarks at 60% lower API price, with a 1M token context window by default.

MiniMax H3 Max Lip Sync turns one photo and one audio clip into a lip-synced talking video with natural expression and head movement, in any language. The outp…

OpenAI's precision-tier GPT Image 2.5 model: heavier than Flare, tighter control across edits and subject preservation for premium creative/production workflow…

OpenAI's fastest GPT Image 2.5 tier: higher quality than GPT Image 2 at 50% lower latency, the default for everyday high-quality generation. Text+image input, …

Meta's Muse Spark 1.3: multimodal reasoning model tuned for longer-horizon agentic, multi-agent and coding workflows, ~20% fewer tool calls than 1.2. Omni-moda…

(50% off until Aug 30!) - Wan 3.0 generates video from a text prompt or a starting image, with cinematic motion and support for 480p, 720p, and 1080p output up…

Google's most intelligent Flash-tier model, GA 2026-09-02: significant gains over 3.7 Flash on software engineering, agentic tasks and multi-step reasoning. 1.…

Tripo P1 image-to-3D: one image → clean, engine-ready low-poly mesh with stable topology in seconds. Ideal for game props, web viewers and real-time pipelines.

Tripo P1: native 3D diffusion that generates clean, engine-ready low-poly meshes with stable topology in seconds — built for Unity/Unreal, web and real-time us…

High-detail reconstruction from several views of the same object (2–4 images): the most accurate Tripo route for characters, products and collectibles, with op…

Tripo's high-detail image-to-3D: one photo or concept render → production-ready mesh with PBR textures; 'Detailed' geometry preserves cloth folds, armor edges …

Tripo's high-detail generation: text prompt → production-ready 3D mesh with PBR textures. 'Detailed' geometry unlocks high-poly output (up to ~2M faces) for he…

Builds a 3D mesh from up to four views of the same object (front required; left, back, right optional) for far better back-side and silhouette accuracy than a …

Turns a single image into a textured 3D mesh (GLB) with optional PBR materials, HD textures and quad topology. Tripo's proven 2.5 generation via fal.

Mistral AI's current flagship: 675B/41B-active MoE, Apache 2.0 open weights, 262K context, tool calling and structured outputs.

Meta's Muse Image model — faithful instruction-following and high visual fidelity, with accurate rendering of fine details like text, plots, and QR codes.

MiniMax Speech 2.8 HD: the studio-quality tier of MiniMax's multilingual speech, same system voice library. Served via OpenRouter.

MiniMax Speech 2.8 Turbo: fast multilingual speech with MiniMax's system voice library. Served via OpenRouter.

Canopy Labs' Orpheus 3B: Llama-based open TTS with seven emotive English voices. Served via OpenRouter.

Sesame CSM-1B: the open conversational speech model behind Sesame's voice companions, with conversational and read-speech presets. Served via OpenRouter.

Fish Audio S2 Pro: expressive multilingual speech with a natural default voice. Served via OpenRouter.

Alibaba's Qwen Audio 3.0 TTS Plus: the higher-quality tier of Qwen's bilingual speech synthesis. Served via OpenRouter.

Alibaba's Qwen Audio 3.0 TTS Flash: fast bilingual (Chinese/English) speech synthesis. Served via OpenRouter.

Kokoro-82M: the tiny open-weight TTS model with 54 voices (American/British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, Chinese) at a fract…

Deepgram Aura-2: 90 natural voices across English, Spanish, French, German, Italian, Dutch, Japanese and more, tuned for real-time narration. Served via OpenRo…

Mistral's Voxtral Mini TTS: 30 voice presets that combine a speaker with an emotion (neutral, happy, sad, excited, angry…) in English, British English and Fren…

Microsoft MAI-Voice-2 Flash: the faster, cheaper tier of MAI-Voice-2 with the same four multilingual voices. Served via OpenRouter.

Microsoft MAI-Voice-2: high-fidelity multilingual text-to-speech (EN, ES, FR, DE voices). Served via OpenRouter.

xAI's Grok Voice text-to-speech: five expressive English voices (Eve, Ara, Rex, Sal, Leo). Served via OpenRouter, billed per 1k characters.

Meta's Muse Spark 1.2 flagship: omni-modal input (text, image, video, audio, files), 1M-token context, Meta's successor to the Llama line. Served via OpenRoute…

Tencent's Hunyuan Hy4 (preview): 1M-token context text model with switchable reasoning, the newest Hunyuan LLM tier. Served via OpenRouter.

Alibaba's fast, low-cost Qwen3.8 tier: multimodal input, 1M-token context, tuned for coding, agents and vision tasks. Served via OpenRouter.

Alibaba's Qwen3.8 Max flagship: natively multimodal (text, image, video input), 1M-token context, deep reasoning. Served via OpenRouter.

Z.ai's flagship GLM-5.3: hybrid sparse + linear attention, 1.3M-token context, strongest GLM tier for long-horizon coding and agent work. Served via OpenRouter.

MiniMax H3 Max Image-to-Video animates a still image into a 5-15 second clip with native synchronized audio, and can optionally interpolate to a supplied end f…

MiniMax H3 Max is a post-trained build of MiniMax H3 that generates 5-15 second videos with native synchronized audio. It ranks #1 in human preference evaluati…

Zhipu AI's 320B-A18B natively multimodal MoE with a 1M token context window, supersedes the GLM-5.2 base tier.

Google's coding/agent-focused Flash tier with a 1.05M token context window, GA since 2026-08-13.

Generate video from a text prompt with Pika 2.2 — fast, stylized text-to-video with 720p/1080p output.

Qwen-Image-3.0-Pro generates and edits images with dense, accurate text rendering, complex multi-element layouts, and photographic detail.

Z.AI's open-weights flagship: beats GPT-5.5 on multiple long-horizon coding benchmarks, 1M token context, 131K output.

Generate full-length songs or instrumentals from a text prompt, with optional auto-generated lyrics

Fast video generation with text-to-video and image-to-video, portrait and landscape support, synchronized audio, and frame interpolation. Up to 20 seconds at 1…

ByteDance's flagship text-to-image and image editing model, generating sharp 1K and 2K images from text or up to 10 reference images

xAI's Grok Imagine Image 2.0 — text-to-image generation and editing with a quality control and output up to 2k

Meta Muse Glimmer 30B is an Apache-2.0 open-weight 30B dense agentic model from Meta, built for long tool-call sequences, hosted on Together AI.

Gemini 3.1 Pro is Google's current Pro-tier flagship reasoning model, GA on the Gemini API with a 1M token context window.

GPT-5.6 Luna is OpenAI's budget tier in the GPT-5.6 family, offering a 1.05M token context window at a lower price point than Sol or Terra.

ByteDance's flagship multimodal video model with native audio, native 30-second generation, and large multimodal reference sets.

OpenAI GPT-5.6 Terra — balanced mid-tier reasoning model between Sol (flagship) and Luna (cost-efficient)

Moonshot AI's current flagship: 2.8T-parameter MoE (16-of-896 experts active), Kimi Delta Attention, native vision, 1M token context.

A powerful native multimodal model for image generation (PrunaAI squeezed)

Google's fastest, cheapest current Flash tier (~350 tok/s) — GA July 2026, for high-volume low-latency text tasks.

Google's current Flash-tier model, GA July 2026 — successor to Gemini 3.5 Flash with faster throughput and the same agentic/coding focus.

Anthropic's newest Opus-tier flagship, released July 2026 — successor to Opus 4.8 with the same pricing tier, built for long-horizon agentic work, knowledge ta…

Moonshot AI's 1T-parameter MoE flagship (32B active), 256K context

xAI's current flagship model, trained with Cursor

Luma Uni-1 Max — higher-quality tier than Uni-1, 2K resolution.

Luma autoregressive image model, matches/beats GPT Image and Nano Banana quality at lower cost. 2K resolution.

The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editin…

Alibaba's flagship closed-weight Qwen text model with a 1M-token context window, agent-grade reasoning and tool use.

PixVerse's flagship video generation model. Generate cinematic videos with synchronized audio, multi-shot sequences, and precise camera control.

High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

DeepSeek's fast, low-cost flagship model with 1M token context and dual thinking/non-thinking modes

Anthropic's Claude Sonnet 5 — near-Opus quality on coding and agentic work at Sonnet-tier speed and cost, with adaptive thinking.

Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model

Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images. Supports 720p and 1080p, 3-15 …

Krea's flagship foundation image model. Larger and more flexible than Krea 2 Medium, with particular strength in photorealism and expressive artistic styles.

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

OpenAI's GPT-5.6 flagship reasoning model

xAI's reasoning flagship model, successor to Grok 4

DeepSeek's flagship reasoning model with 1M token context

Google's most intelligent Flash-tier model for sustained frontier performance on agentic and coding tasks. Fully GA as of May 2026, succeeding Gemini 2.5 Flash.

Anthropic's fastest and most cost-effective current model — ideal for simple, speed-critical tasks. The platform's first Anthropic fast/cheap tier.

Anthropic's most capable widely released model — for the most demanding reasoning and long-horizon agentic work. A new tier above Opus, with a 1M token context…

Anthropic's most capable Opus-tier model — highly autonomous, state-of-the-art on long-horizon agentic work, knowledge work, and memory, with clearer, warmer w…

Alibaba's Happy Horse 1.0 generates videos from text prompts or animates a single image into video. Supports 720p and 1080p, 3-15 second durations, and five as…

High-fidelity video generation with portrait support, audio-to-video, retake, and extend. Text, image, and audio-driven creation up to 4K at 50 FPS.

Google's cost-efficient video generation model with native audio, optimized for high-volume applications

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model

The highest quality Ideogram v4 model. v4 creates images with stunning realism, creative designs, and consistent styles

OpenAI GPT-5.4 — latest generation language model with improved reasoning and creativity

Very fast image generation. 4-step distilled, sub-second inference for production and real-time applications.

Max-quality image generation and editing with typography and up to 10 reference images.

The highest fidelity image model from Black Forest Labs. Superior prompt understanding, editing consistency, and multi-reference support.

OpenAI GPT Image 2 — state-of-the-art image generation and editing model. Highest performance with flexible image sizes, high-fidelity inputs, and precise iter…

PixVerse v5 — latest PixVerse with lifelike physics and striking visuals.

PixVerse v4.5 — upgraded version with improved motion quality and prompt adherence.

PixVerse v4 — video generation model supporting text-to-video and image-to-video up to 1080p.

WaveSpeed AI serving Wan 2.1 image-to-video at 480p. Cheaper draft-tier.

WaveSpeed AI serving Wan 2.1 image-to-video at 720p.

WaveSpeed AI serving Wan 2.1 text-to-video at 720p.

Alibaba Wan 2.5 T2V Fast — fast variant of Wan 2.5 text-to-video for quick iteration.

Alibaba Wan 2.2 T2V Fast — fast text-to-video at 480p. Cheap and quick for iteration.

OpenAI Sora 2 Pro — highest-fidelity Sora 2 tier for premium cinematic video. Text-to-video and image-to-video.

OpenAI Sora 2 — flagship video model with cinematic quality, strong physics simulation, and precise prompt adherence. 4-12s at 720p/1080p.

Kling 2.6 — text-to-video and image-to-video with native audio. 5-10s with motion prompts and negative prompts.

Kling 2.5 Turbo Pro — image-to-video with cinematic motion and precise intent following. Up to 10s.

Pruna AI's multimodal video model built for speed and iteration — supports text, image, and audio-to-video in a unified endpoint. 1-10s, up to 1080p.

Alibaba Wan 2.7 VideoEdit — instruction-based video editing model. Modify an existing clip with natural-language instructions: background swaps, lighting, styl…

OpenAI GPT Image 1.5 — latest flagship image gen/edit model with stronger preservation, precise iterative edits, up to 4x faster than GPT Image 1. Built on GPT…

Ideogram v3 Quality — highest fidelity variant of Ideogram v3 for premium graphic design and typography work.

Ideogram v3 Turbo — fast, design-focused image generation with best-in-class typography, accurate text rendering and graphic design quality at a low price.

ByteDance Seedream 5 Lite — lightweight variant of Seedream 5 with built-in multi-step reasoning, example-based editing, and deep domain knowledge. Up to 3K.

ByteDance Seedream 4.5 — upgraded unified image generation and editing model with stronger spatial understanding, world knowledge, and cinematic visuals. Up to…

MiniMax Hailuo 2.3 Pro image-to-video (1080p) on fal.ai — flagship tier for quality.

Kling Video v3 Pro image-to-video on fal.ai — cinematic visuals, fluid motion, native audio, element referencing. Up to 15s.

ByteDance Seedance 2.0 Fast — speed-optimized variant of Seedance 2.0 with native audio-video joint generation. Supports text-to-video and image-to-video at 48…

MiniMax Hailuo 2.3 Fast — faster and cheaper variant of Hailuo 2.3 for quick iterations.

MiniMax Hailuo 2.3 — latest flagship video model with improved motion, physics, and prompt adherence. Supports text-to-video and image-to-video up to 1080p.

Alibaba Wan 2.7 — newest 27B open-weights video model. Generates up to 15s 1080p with native audio-sync from text prompts.

Google Veo 3.1 Fast — faster, cheaper variant of Veo 3.1 with native audio. Great for high-volume production.

Google Veo 3.1 — state-of-the-art text-to-video model with native audio generation, natural lip sync, cinematic quality, and strong prompt adherence. Up to 108…

Latest balanced AI model combining speed with intelligence—analyzes images, processes large documents, and excels at programming tasks with multilingual support

Latest balanced AI model combining speed with intelligence—analyzes images, processes large documents, and excels at programming tasks with multilingual support

Latest balanced AI model combining speed with intelligence—analyzes images, processes large documents, and excels at programming tasks with multilingual support

Google's fast image generation model with conversational editing, multi-image fusion, and character consistency

ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control. Supports text-to-video and imag…

State-of-the-art video motion quality, prompt adherence and visual fidelity

Cinematic videos up to 15 seconds with multi-shot control, native audio, and improved consistency.

Unified multimodal video generation with reference images, video editing, native audio, and multi-shot control.

Transfer motion from a reference video to any character image with improved consistency and quality.

Generate videos using xAI Grok Imagine Video model. Fast ~30s generation with audio.

Personalized Image Animator

RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

Mochi 1 preview is an open video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation

Create 5s 480p videos from a text prompt

Training-free Controllable Text-to-Video Generation

Generate high quality videos from a prompt

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resoluti…

Create tileable animations with seamless transitions

Use Runway's Stable-diffusion inpainting model to create an infinite loop video

Animate Stable Diffusion by interpolating between two prompts

VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing

🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives

Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)

Animate Your Personalized Text-to-Image Diffusion Models

🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL

Zeroscope V2 XL & 576w

Text-to-Image Diffusion Models are Zero-Shot Video Generators

Multi-stage text-to-video generation

Runway Gen-4.5 — highest quality video generation model with state-of-the-art motion and visual fidelity

Runway Gen-4 Turbo — fast, high-quality video generation from images with improved motion coherence and cinematic controls

Generate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths — clean layers, editable outp…

Generate production-ready SVG vector images from text prompts. Recraft V4's design taste applied to vector output — clean geometry, structured layers, and edit…

Recraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-sc…

Recraft's latest image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and c…

P-Image Edit by Pruna AI edits reference images using text instructions. Generation starts at 40 coins. Review the quote before sending; settings can change th…

P-Image by Pruna AI creates images from text prompts. Generation starts at 20 coins. Review the quote before sending; settings can change the price. Supports m…

Crystal Upscaler is a high-precision AI image upscaler optimized for portraits, faces, and product photography, powered by Clarity AI technology. This speciali…

SeeDANCE 1.5 Pro by ByteDance is a revolutionary joint audio-video AI model that generates cinematic videos with synchronized audio from text descriptions or i…

FLUX 2 Pro by Black Forest Labs is a professional-grade AI image generator designed for brand consistency and creative control. This advanced text-to-image and…

Wan 2.5 T2V (Text-to-Video) by Alibaba is an advanced AI video generator that creates cinematic videos from text descriptions with optional audio synchronizati…

Wan 2.5 Image to Video (I2V) by Alibaba is a powerful AI animator that transforms static images into cinematic videos with optional background audio synchroniz…

Seedream 4 by ByteDance is a unified AI image generation and editing model capable of creating stunning images up to 4K resolution (4096×4096 pixels) from text…