Creative AI tools, explained plainly

What each AI tool for pictures, video, voice, music, presenters and 3D actually does, what it costs, whether it’s open or closed, and whether you can sell what you make. Every fact links to its source and shows when it was last checked.

307 entries: 225 tools, 74 models and 8 places to run them. Built by a newcomer, for newcomers. Nobody pays to be listed or ranked.

What do you want to make?

• A picture (115 entries)
• A video (149 entries)
• A voice or speech (102 entries)
• Music and sound (53 entries)
• A talking presenter (55 entries)
• A 3D object or scene (37 entries)

Every entry, A to Z

• 3D AI Studio: A browser studio that turns a text prompt or a picture into a 3D model, using its own engines plus models from other makers. (Tool, Closed)
• ACE-Step: A free, downloadable model that writes whole songs, with or without vocals, from a text description and lyrics. (Model, Fully open, free option)
• Adobe Express: An easy design app for social posts, flyers, logos and short videos, with templates and built-in AI to make images from a description, remove backgrounds and edit photos. (Tool, Closed, free option)
• Adobe Firefly: Adobe's AI studio for making and editing pictures from text, plus short videos, voiceovers, music and sound effects. (Tool, Closed, free option)
• Adobe Lightroom: Adobe's photo organiser and editor for photographers. (Tool, Closed, free option)
• Adobe Photoshop: Adobe's long-standing photo editor, now with AI built in. (Tool, Closed)
• Adobe Podcast (Enhance Speech): A browser tool that makes speech recorded on a phone or laptop sound like it was done in a quiet studio by removing background noise and echo. (Tool, Closed, free option)
• Adobe Premiere: Adobe's professional video editor. (Tool, Closed, free option)
• Adobe Substance 3D: Adobe's set of desktop apps for professional 3D texturing, materials, modelling and scene rendering. (Tool, Closed)
• AI Studios by DeepBrain AI: DeepBrain AI's AI Studios turns a script into a video with a digital presenter, can dub videos into other languages, and offers presenters people can talk to live. (Tool, Closed, free option)
• AIVA: Writes instrumental music for you from a chosen style, which you can then edit note by note. (Tool, Closed, free option)
• Akool: A large web toolkit for AI video: talking presenters, talking photos, face swap (including live), video translation and voice cloning, plus picture and video makers that run many other companies' models. (Tool, Closed, free option)
• Amazon Polly: Amazon's cloud service that reads text aloud in dozens of voices and languages. (Tool, Closed, free option)
• Anam: Builds realistic AI faces that hold live video conversations, for example as a support agent or tutor on a website. (Tool, Closed, free option)
• Animoto: A long-running browser video maker: drop your photos and clips into ready-made templates, add licensed music and text, and export. (Tool, Closed, free option)
• Aragon AI: Upload a few selfies and get a set of professional-looking headshots of yourself in about half an hour, in chosen outfits and backgrounds. (Tool, Closed)
• Arcads: Makes video adverts in the style of social-media testimonials, using a library of AI actors who read your script. (Tool, Closed)
• Argil: Makes short social-media videos with a digital copy of you, or a stock presenter, speaking your script. (Tool, Closed, free option)
• Artbreeder: A playful browser tool for making pictures by mixing images and text, blending 'genes' of portraits, making collages and extending images. (Tool, Closed, free option)
• AssemblyAI: A speech-to-text service for developers: send it recordings or live audio and get back text, with options such as who-said-what, translation and summaries. (Tool, Closed, free option)
• Async (formerly Podcastle): An online studio for podcasts and videos: record remote guests, get transcripts, clean up and edit audio, and turn text into speech with AI voices. (Tool, Closed, free option)
• AudioGen (medium): A downloadable model from Meta that makes short sound effects, like a dog barking or footsteps, from a text description. (Model, Downloadable, with conditions, free option)
• AudioShake: Splits audio into separate parts: vocals and instruments in a song, or dialogue, music and effects in a film soundtrack. (Tool, Closed, free option)
• Auphonic: Upload a podcast or recording and it automatically evens out volume, reduces noise and hum, cuts silences and filler words, and can write a transcript. (Tool, Closed, free option)
• Autodesk Flow Studio: An online tool that reads ordinary filmed footage and rebuilds it as a 3D scene: it tracks the camera, captures actors' body, face and hand movement without suits, and lets you drop animated CG characters into the shot. (Tool, Closed, free option)
• Azure AI Speech: Microsoft's cloud speech service for developers and businesses. (Tool, Closed, free option)
• BandLab SongStarter: A song-idea generator inside the BandLab music studio. (Tool, Closed, free option)
• Bark: A free, downloadable model that turns text into speech in 13 languages, and can add laughs, sighs, background noise or a little music. (Model, Fully open, free option)
• Beatoven.ai: Makes royalty-free background music and sound effects from a short written description, in your browser. (Tool, Closed)
• BiRefNet: A free, open model that cuts the main subject out of a photo with fine detail such as hair, so you can remove or replace the background. (Model, Fully open, free option)
• Blockade Labs Skybox AI: Makes a 360-degree surrounding scene (a skybox) from a short description, for use as a backdrop in games, VR or 3D scenes. (Tool, Closed)
• Boomy: A website that uses AI to make music for you. (Tool, free option)
• Bria: A business service for making and editing images (and some video clean-up) through an API, plugins and web tools, using Bria's own models trained on licensed stock images. (Tool, Closed, free option)
• CAMB.AI: Translates and dubs videos and live streams into other languages, and turns text into natural-sounding speech, using its own MARS speech models. (Tool, Closed, free option)
• Canva AI (Magic Studio): The AI tools built into the Canva design app: make pictures from a description, edit photos by pointing and clicking, remove backgrounds and resize designs. (Tool, Closed, free option)
• CapCut: A video editor with templates and basic editing tools, plus paid AI credits for making short clips from a description using ByteDance's Seedance video models. (Tool, Closed, free option)
• Captions: A phone and web video editor for talking-to-camera clips. (Tool, Closed, free option)
• Cartesia: A fast text-to-speech and speech-to-text service aimed at developers building voice apps and phone agents. (Tool, Closed, free option)
• ChatGPT Images: Make and edit pictures by chatting with ChatGPT: describe what you want or upload a photo and ask for changes. (Tool, Closed, free option)
• Chatterbox: A free, downloadable family of text-to-speech models from Resemble AI that read text aloud in 23 languages and can copy a voice from a short clip. (Model, Fully open, free option)
• Civitai: A large community site for sharing and downloading Stable Diffusion and Flux models and add-ons, with an on-site generator for pictures and video paid for with its 'Buzz' currency. (Place to run it, free option)
• Claid: Online tools for shop product photos: put a product into a styled scene, show clothes on AI fashion models, remove backgrounds, upscale and fix lighting, or turn a still into a short video. (Tool, Closed, free option)
• Cleanup.pictures: A simple browser tool for erasing unwanted things from a photo: paint over a person, object, text or blemish and it fills the gap. (Tool, Closed, free option)
• Cleanvoice AI: Cleans up podcast and voice recordings in your browser: removes background noise, filler words like 'um', mouth sounds and long silences, and can transcribe and summarise. (Tool, Closed, free option)
• Clipchamp: Microsoft's simple video editor for the browser and Windows. (Tool, Closed, free option)
• Clipdrop: A set of quick photo tools in the browser: remove or replace a background, erase objects, widen a picture, relight it, upscale it, or make an image from a description. (Tool, Closed, free option)
• CogVideoX: A downloadable video model from the Z.ai (Zhipu) CogVideoX team that makes 5-10 second clips from a description or a photo. (Model, Downloadable, with conditions, free option)
• Colossyan: Turns a script into a video with a digital presenter, aimed at workplace training. (Tool, Closed, free option)
• ComfyUI: A free, open-source app where you build image, video, audio and 3D workflows by linking boxes together, running open models on your own computer. (Tool, Fully open, free option)
• Creatify: Makes short video and image adverts, often from a product link, using stock AI presenters reading a script. (Tool, Closed, free option)
• CSM (Cube): Turns a picture or a short description into a 3D model in your browser, and can split an object into separate parts, tidy up the mesh and repaint textures. (Tool, Closed, free option)
• D-ID: Makes a photo or video of a face talk, reading your script or audio. (Tool, Closed)
• DaVinci Resolve: Professional desktop software for editing, colour, effects and sound. (Tool, Closed, free option)
• Deepgram: A pay-as-you-go service for developers that turns speech into text (live or from files) and text into speech, priced per minute or per character. (Tool, Closed, free option)
• DeepMotion Animate 3D: Upload an ordinary video of someone moving and get the movement back as 3D character animation (motion capture without a suit), ready to use in games or 3D apps. (Tool, Closed, free option)
• DeeVid AI: A browser and phone app that makes short videos and pictures from a description or a photo, using a choice of other makers' video models. (Tool, Closed, free option)
• Demucs: A free, open model that splits a song into separate drums, bass, vocals and other parts (a six-part version adds guitar and piano). (Model, Fully open, free option)
• Descript: Edit audio and video by editing a written transcript, like a document. (Tool, Closed, free option)
• Dia: A free, downloadable speech model that turns a written two-person script into spoken dialogue, including laughs and coughs. (Model, Fully open, free option)
• DiffusionBee: A free Mac app that runs Stable Diffusion image models on your own computer, offline. (Tool, Fully open, free option)
• Distil-Whisper: A smaller, faster version of OpenAI's Whisper that turns English speech into text, about six times quicker than the full model. (Model, Fully open, free option)
• DomoAI: A browser app that turns photos, descriptions or existing clips into short animated videos, including anime-style restyling and talking avatars. (Tool, Closed)
• Draw Things: A free app for iPhone, iPad and Mac that makes pictures on your own device, offline, using downloadable open models. (Tool, free option)
• Dreamina: A CapCut web app that makes pictures and short videos from a description or a photo, edits and upscales images, and creates talking avatars. (Tool, Closed, free option)
• Dubverse: A web tool that translates and re-voices your videos into other languages with AI voices, and also makes subtitles and text-to-speech. (Tool, Closed)
• Dzine: A browser app for making and editing pictures and short videos with AI, with a canvas for layered edits, consistent characters, lip sync and talking avatars. (Tool, Closed, free option)
• EchoMimic: A free, downloadable model from Ant Group that makes a photo of a person talk or sing in time with an audio clip. (Model, Fully open, free option)
• Elai.io: Makes training and explainer videos with a virtual presenter reading your script. (Tool, Closed, free option)
• Eleven Music: ElevenLabs' song maker: describe a song and get music with or without singing, in several languages, then regenerate single sections like the chorus. (Tool, Closed, free option)
• Eleven v3: ElevenLabs' expressive text-to-speech model. (Model, Closed, free option)
• ElevenLabs: Type text and get natural-sounding speech in many languages, or make a copy of your own voice. (Tool, Closed, free option)
• F5-TTS: A free research text-to-speech model that copies the voice in a short reference clip and reads new text in it. (Model, Downloadable, with conditions, free option)
• Facetune: A phone and browser app for touching up selfies and short videos: smooth skin, change makeup, hair or outfits, remove backgrounds and make AI headshots. (Tool, Closed, free option)
• fal: A pay-as-you-go service for running many AI models through code or a web playground: image, video, speech, 3D, and talking-avatar and lip-sync models from various makers. (Place to run it, Closed)
• FantasyTalking: A free research model that makes a portrait photo talk: give it a picture and a voice recording and it produces a video of the person speaking with matching lips and head movement. (Model, Fully open, free option)
• Filmora: A video editing app for computers and phones from Wondershare, with built-in AI extras: make clips from a description or photo, lengthen clips, auto captions, text to speech, music and sound effects. (Tool, Closed, free option)
• Fish Audio: A text-to-speech site with a large library of community voices. (Tool, Closed, free option)
• Flair: A browser tool for online shops that stages product photos in AI-made scenes, puts clothing and jewellery on AI-generated models, and makes short product videos and ads. (Tool, Closed, free option)
• FlexClip: A browser video editor with templates and many AI helpers: turn a prompt, article or slides into a video, add AI voiceovers, subtitles and music, remove backgrounds and make AI images. (Tool, Closed, free option)
• Fliki: Turns a script, idea, blog post or slides into a narrated video with stock visuals, AI voices and optional avatars. (Tool, Closed, free option)
• FLUX.1 [dev]: A downloadable model that turns a written description into a picture. (Model, Downloadable, with conditions, free option)
• FLUX.1 [schnell]: A fast, free-to-download model that turns a description into a picture in a few steps. (Model, Fully open, free option)
• FLUX.1 Kontext: A model that changes an existing picture from a written instruction, such as swapping the background or restyling it, while keeping the same character. (Model, Downloadable, with conditions, free option)
• FLUX.2: A family of picture models from Black Forest Labs that make and edit images from text, and can combine several reference images. (Model, Downloadable, with conditions, free option)
• FLUX1.1 [pro]: A picture-making model from Black Forest Labs that turns a written description into an image. (Model, Closed)
• Fooocus: A free, open-source program you install on your own computer to make pictures from a description with few settings to learn. (Tool, Fully open, free option)
• Fotor: An all-in-one photo editor and design app with AI tools: make pictures or short videos from a description, edit photos, remove backgrounds and get AI headshots. (Tool, Closed, free option)
• Gemini 2.5 Flash Image (Nano Banana): Google's first 'Nano Banana' image model. (Model, Closed)
• Genmo: A video lab that makes short clips from a written description. (Tool, Closed, free option)
• getimg.ai: A browser workspace for making and editing pictures with many different AI models, plus video, music, speech and sound effects. (Tool, Closed)
• Gling: An editing helper for people who film themselves talking, such as YouTubers. (Tool, Closed, free option)
• Google Cloud Text-to-Speech: Google's developer service that turns written text into spoken audio in many voices and languages, paid per character. (Tool, Closed, free option)
• Google Flow: Google's browser studio for making short video clips and pictures from a description, a photo or reference images, then editing and stitching them into scenes. (Tool, Closed, free option)
• Google Flow Music: Google's music app where you chat with an assistant to make full songs with vocals, remix tracks, split songs into parts and make music videos. (Tool, Closed, free option)
• Google Flow Music (formerly MusicFX): Google's MusicFX page now leads to Google Flow Music, where you chat with an assistant to make full songs with vocals, remix tracks and split songs into parts. (Tool, Closed, free option)
• Google Flow Music (formerly Riffusion): Riffusion's web address now leads to Google Flow Music, where you chat with an assistant to make full songs with vocals, remix tracks and split songs into parts. (Tool, Closed, free option)
• Google Gemini (image creation): Image making inside Google's Gemini chat app: describe a picture or upload photos and ask for changes in plain words. (Tool, Closed, free option)
• GPT Image 1: OpenAI's earlier model for making and editing pictures from text and reference images, used through OpenAI's API. (Model, Closed)
• Hailuo AI: A browser app from MiniMax for making short video clips from a description or a photo, plus pictures and ready-made effect templates. (Tool, Closed, free option)
• Hallo2: A free, downloadable research model that animates a front-facing portrait photo to speak along with an English audio track, including long clips and an optional sharper high-resolution mode. (Model, Downloadable, with conditions, free option)
• Happy Scribe: Upload a recording or video and get a written transcript or subtitles, which it can also translate into other languages. (Tool, Closed, free option)
• HeadshotPro: Upload a few selfies and get a set of professional-looking work headshots made by AI. (Tool, Closed)
• Hedra: Makes any face in a picture talk or sing along to an audio track, using its own Character 3 model or others it hosts. (Tool, Closed, free option)
• HeyGen: Makes videos of a digital presenter reading your script, in your browser. (Tool, Closed, free option)
• HiDream-I1: A large downloadable model (17 billion parameters) that makes pictures from a description. (Model, Fully open, free option)
• Higgsfield: A web app that runs several makers' video and image models in one place, such as Seedance and Nano Banana. (Tool, Closed)
• HitPaw VikPea: A desktop app that uses AI to make old, blurry or low-resolution videos sharper and bigger (up to 8K), smoother or colourised. (Tool, Closed, free option)
• Hour One: Makes videos of a virtual presenter reading your text or slides, in several languages. (Tool, Closed, free option)
• Hugging Face: The main public library of AI models, where makers publish open models for pictures, video, speech, music and 3D. (Place to run it, free option)
• Hume AI: A company known for expressive AI voices. (Tool, Closed)
• Hunyuan 3D (Tencent): Tencent's web app for making 3D models from a description, up to four photos or a sketch, with tools to tidy the mesh and export OBJ or GLB for games, shops or 3D printing. (Tool, Closed, free option)
• Hunyuan3D 2: Tencent's downloadable 3D model maker: one part builds a shape from a picture, another paints textures onto it. (Model, Downloadable, with conditions, free option)
• HunyuanVideo: A free, downloadable video model from Tencent with about 13 billion parameters. (Model, Downloadable, with conditions, free option)
• HunyuanVideo-Avatar: A free-to-download Tencent model that makes a still portrait talk or sing in time with an audio track, with control over emotion and support for more than one character. (Model, Downloadable, with conditions, free option)
• Hyper3D Rodin: Makes a textured 3D model from one or more photos or a text description, in your browser. (Tool, Closed, free option)
• Ideogram: Makes pictures from a written description and is especially good at putting readable words into images, such as posters and logos. (Tool, Closed, free option)
• Imagen 4: Google's text-to-picture model, offered to developers in Fast, Standard and Ultra versions through Google's APIs. (Model, Closed)
• ImagineArt: An all-in-one creative site for pictures, video and audio. (Tool, Closed, free option)
• InfiniteTalk: A free, downloadable model that makes a person in a video or photo speak along to a new audio track, moving lips, head and body to match. (Model, Fully open, free option)
• InstantMesh: A free research model from Tencent ARC that turns a single picture of an object into a 3D mesh quickly. (Model, Fully open, free option)
• invideo AI: A browser video editor where you describe changes in plain words and an AI agent makes them on a timeline. (Tool, Closed)
• Invoke (InvokeAI): A free, open-source app you install to make and edit pictures with open models like Stable Diffusion and FLUX on your own computer, with a layered canvas and workflow builder. (Tool, Fully open, free option)
• iZotope Ozone: Mastering software that runs inside music apps such as Logic or Ableton. (Tool, Closed)
• Jogg AI: Makes marketing and product videos with a digital presenter reading your script. (Tool, Closed, free option)
• Kaedim: A 3D modelling service for game studios and brands: you send sketches, photos or briefs, and its AI plus in-house artists return game-ready 3D models. (Tool, Closed)
• Kaiber: A creative app for making stylised videos and images, including music-synced videos that move to the beat of a track. (Tool, Closed)
• Kapwing: An online video editor that works in your browser. (Tool, Closed, free option)
• KIRI Engine: A phone and web app that turns photos or a video of a real object or room into a 3D model (3D scanning). (Tool, Closed, free option)
• Kits AI: Music-focused voice tools: turn a sung or spoken take into another voice, clone your own singing voice, and split songs into vocals and instruments. (Tool, Closed, free option)
• Kittl: A browser design app for logos, merch, packaging and social graphics. (Tool, Closed, free option)
• Klap: A web tool that turns a long video, such as a YouTube upload, into short vertical clips for TikTok, Reels and Shorts. (Tool, Closed, free option)
• Kling 2.5 Turbo: Kuaishou's September 2025 video model behind the Kling AI app. (Model, Closed)
• Kling AI: An app for making short video clips from a description or a photo, with tools to copy movement from one clip to another and to edit results. (Tool, Closed, free option)
• Kokoro-82M: A small, free text-to-speech model that reads text aloud in 54 voices across 8 languages. (Model, Fully open, free option)
• Krea: A browser studio that makes and edits pictures and short videos from a description, using Krea's own models plus many from other makers. (Tool, Closed, free option)
• Krisp: Runs alongside your video-call apps to remove background noise and echo from your voice, transcribe meetings and write notes. (Tool, Closed)
• LALAL.AI: Splits a song into separate parts such as vocals, drums, bass and guitar, and can clean noise or echo from voice recordings. (Tool, Closed, free option)
• LANDR: A toolkit for home musicians: automatic AI mastering to make a finished track sound polished, a stem splitter, a large sample library, plugins, and release to streaming services. (Tool, Closed, free option)
• LatentSync: A free, downloadable lip-sync model from ByteDance. (Model, Fully open, free option)
• Lensa: A phone photo editor that uses AI for one-tap looks, retouching, removing unwanted objects, sharpening old or dark photos and trying on hairstyles; it can also make stylised avatars of you from selfies. (Tool, Closed, free option)
• Leonardo.Ai: A browser app for making and editing pictures and short videos from a description. (Tool, Closed, free option)
• Let's Enhance: Makes photos sharper and bigger in your browser: upscales, removes noise and blur, and restores old pictures. (Tool, Closed, free option)
• Lexica: A website where you can search a large gallery of AI-made images and make your own from a description. (Tool, Closed, free option)
• Listnr AI: A browser text-to-speech tool: paste text and get a voiceover in one of 1,000+ voices and 140+ languages, for videos, audiobooks or podcasts. (Tool, Closed, free option)
• LivePortrait: A free, downloadable model from Kuaishou that animates a still portrait by copying the head movements and expressions from another video. (Model, Fully open, free option)
• Looka: Makes logo ideas from your business name and style choices, then lets you tweak colours, symbols and fonts. (Tool, Closed, free option)
• Loudly: A browser music studio that makes instrumentals or full songs with vocals from a description, and can split songs into parts, remix tracks you own, master them and send them to streaming services. (Tool, Closed, free option)
• LOVO AI: A browser tool for making voiceovers from a script, with a library of ready-made voices and the option to clone voices on paid plans. (Tool, Closed)
• LTX Studio: A browser workspace from Lightricks for planning and making short films: write or upload a script, turn it into a storyboard, then generate and edit the shots with LTX and other makers' models. (Tool, Closed, free option)
• LTX-Video: A downloadable video model from Lightricks that makes short clips from a description, a photo or a bit of video. (Model, Downloadable, with conditions, free option)
• Luma Dream Machine: Luma's app for making short video clips from a description or a photo, restyling video you have, and making pictures. (Tool, Closed, free option)
• Luma Photon: Luma AI's picture-making model. (Model, Closed)
• Luma Ray3: Luma's video model for making short clips from a description or a photo, or for restyling a video you already have. (Model, Closed)
• Lumen5: A browser tool aimed at businesses that turns written text, such as an article or post, into a short social video. (Tool, Closed)
• Luminar Neo: Photo-editing software for computer and phone with AI tools that remove unwanted objects, swap or extend parts of a scene, replace skies, retouch portraits and enlarge photos. (Tool, Closed)
• Lyria 2: Google DeepMind's earlier music model, which turns a text description into a short piece of music. (Model, Closed)
• MacWhisper: A Mac app that turns recordings, videos and meetings into text on your own computer, so audio need not leave your Mac. (Tool, Closed, free option)
• Mage Space: A browser app for making pictures and short videos from a description or a photo, using many open models plus its own tuned ones. (Tool, Closed, free option)
• MAGI-1: A free, open video model from Sand AI that animates a photo, continues an existing clip or makes video from a description, building it chunk by chunk. (Model, Fully open, free option)
• Magic Hour: A web app with dozens of quick AI tools on one credit balance: make or restyle video clips, swap faces, sync lips to new audio, animate a photo, and make images, voices and music. (Tool, Closed, free option)
• Magnific: Began as an AI upscaler that makes images sharper and larger while adding detail. (Tool, Closed)
• Masterpiece X: Makes simple 3D characters, animals and objects from a text description in your browser, for prototypes and concept work. (Tool, Closed, free option)
• Meshcapade: A German company that turned ordinary video into 3D body motion (motion capture without suits) and made digital human body models. (Tool, Closed)
• Meshy: Makes 3D models from a text description or a picture, then can paint textures on them and rig characters so they can move. (Tool, Closed, free option)
• Microsoft Designer: Microsoft's free design app for social posts, cards and invitations. (Tool, Closed, free option)
• Midjourney: Makes artistic pictures from a written description, on its website or in Discord. (Tool, Closed)
• MiniMax Audio: MiniMax's text-to-speech service: a web app and paid API that read text aloud in realistic voices, copy a voice from a 10-second sample, or design a new voice from a description. (Tool, Closed)
• MiniMax Hailuo 02: MiniMax's video model from mid-2025. (Model, Closed)
• Mixar: A free, open-source 3D editor built on Blender where a chat assistant does modelling and texturing steps for you. (Tool, Fully open, free option)
• MMAudio: A research model that adds matching sound effects to a silent video clip, or makes sounds from a text description. (Model, Downloadable, with conditions, free option)
• Mochi 1: A free, downloadable video model from Genmo that turns a description into a short 480p clip. (Model, Fully open, free option)
• Moises: A practice and production app for musicians: it splits any song into parts like vocals, drums and bass, finds chords, writes out lyrics and changes speed. (Tool, Closed, free option)
• Moonvalley: A web app for making short film-style video clips from a description or a photo, with controls for camera moves and for copying movement from a reference clip. (Tool, Closed)
• Move AI: Records how a person moves from ordinary video (an iPhone, or several cameras) and turns it into 3D animation data you can put on a game or film character. (Tool, Closed)
• Mubert: Makes royalty-free instrumental background tracks for videos, streams and apps from a short description or a pick of genre, mood and length. (Tool, Closed, free option)
• Munch: Paste a link to a long video, such as a YouTube upload, and Munch picks out the most engaging moments and turns them into short, phone-shaped clips for social media. (Tool, Closed, free option)
• Mureka: Makes full songs with singing, lyrics and backing music from a short description, in your browser. (Tool, Closed, free option)
• Murf AI: A browser studio for turning a script into a voiceover, choosing from a library of ready-made voices in many languages. (Tool, Closed)
• MuseTalk: A free, downloadable model that changes the lip movements of a face in a video to match new speech, fast enough to run in real time on a strong graphics card. (Model, Fully open, free option)
• Musicfy: Lets you make a song sound as if it were sung by a different voice, either one from its library or a custom voice you train from recordings. (Tool, Closed, free option)
• MusicGen: Meta's downloadable model that turns a short English description, optionally with a hummed or played tune, into instrumental music clips. (Model, Downloadable, with conditions, free option)
• MyEdit: A browser and phone editor with simple AI audio tools: remove or isolate vocals, make music or sound effects from a description, clean up noisy recordings, change your voice and read text aloud. (Tool, Closed, free option)
• Narakeet: Turns typed text into spoken audio, and can build narrated videos from slides or a script. (Tool, Closed, free option)
• NaturalReader: Reads documents, PDFs and web pages aloud in natural-sounding voices. (Tool, Closed, free option)
• NightCafe: A browser app with a big community where you make pictures from a description using many different AI models, and can also make short videos and edit images. (Tool, Closed, free option)
• Notta: Turns meetings, calls and uploaded recordings into written transcripts, with AI summaries and translation. (Tool, Closed, free option)
• NVIDIA Broadcast: A Windows app that uses your NVIDIA graphics card to clean up your mic and webcam live: removes background noise and echo, blurs or replaces your background, and keeps you centred. (Tool, Closed, free option)
• NVIDIA Parakeet: A free speech-recognition model from NVIDIA that turns recordings in 25 European languages into punctuated text with timestamps. (Model, Fully open, free option)
• OmniHuman: A ByteDance model that turns one photo plus a voice or music track into a video of that person talking, singing or moving, from head-and-shoulders up to full body. (Model, Closed)
• Open-Sora: A fully open-source video model (code and weights under Apache 2.0) that turns a description or a photo into a short clip, about 5 seconds long. (Model, Fully open, free option)
• OpenAI Speech API: OpenAI's pay-as-you-go developer service for turning text into speech with a set of ready-made voices, and for turning recordings into text. (Tool, Closed)
• OpenArt: A web studio that lets you pick from many other companies' AI models to make and edit pictures and short videos, keep a character consistent, and add voice or music. (Tool, Closed, free option)
• OpenAudio S1: A text-to-speech model from the team behind Fish Audio that reads text in 13 languages and lets you add emotion tags like (sad) or (whispering). (Model, Downloadable, with conditions, free option)
• OpusClip: Cuts a long video, like a podcast or talk, into short clips for social media, adding captions and reframing for phones. (Tool, Closed, free option)
• Otter.ai: Joins your Zoom, Teams or Google Meet calls and writes down what is said, with speaker names and an AI summary you can ask questions of. (Tool, Closed, free option)
• Parler-TTS: A free, open text-to-speech model for English where you describe the voice in words (for example 'a calm female voice, very clear audio') and it reads your text that way. (Model, Fully open, free option)
• Pebblely: A web app for online sellers: upload a product photo and it puts the item into a new, realistic scene with matching shadows and reflections, ready for shop listings, ads and social posts. (Tool, Closed, free option)
• Photoroom: A phone and web app for product photos. (Tool, Closed, free option)
• Picsart: A popular photo and video editor for phone and web with many AI tools: make pictures from a description, remove backgrounds, enhance photos, and generate video, voice and music using dozens of other makers' models. (Tool, Closed, free option)
• Pictory: A browser video editor that turns a script, blog post or long recording into a narrated video with stock footage, captions and AI voices. (Tool, Closed, free option)
• PicWish: A photo editing app that removes backgrounds, erases objects, sharpens and enlarges pictures, restores old photos and makes product shots. (Tool, Closed, free option)
• Pika: A web app for making short video clips, lengthening clips, swapping things in a scene and adding a matching soundtrack. (Tool, Closed, free option)
• Pixelcut: A photo editor for sellers and small brands: remove backgrounds, sharpen and enlarge photos, and make product shots and short ad videos from a description. (Tool, Closed, free option)
• Pixelmator Pro: A photo and graphics editor for Mac and iPad, now made by Apple. (Tool, Closed)
• Pixlr: A low-cost online photo editor with AI tools: make pictures from text, fill or extend parts of a photo, remove backgrounds and objects, upscale, swap faces and make short videos. (Tool, Closed, free option)
• PixVerse: A web and phone app that turns a description or a photo into a short video clip, with extras such as lip sync, sound effects and extending a clip. (Tool, Closed, free option)
• Plask: Records body and hand movement from an ordinary video and turns it into 3D animation you can put on a character, all in your browser. (Tool, Closed, free option)
• Playground: A browser design studio that makes logos, social posts, posters and T-shirt graphics from a description, with templates and editing tools. (Tool, Closed, free option)
• PlayHT (PlayAI): An online text-to-speech service that reads your text aloud in many voices and languages, with multi-speaker dialogue and an option to copy a voice. (Tool, Closed, free option)
• Pollo AI: A web app that puts many makers' video and image models in one place, such as Seedance, Veo, Sora, Kling and Wan, plus its own Pollo model. (Tool, Closed, free option)
• Poly (withpoly): Poly used to make tileable textures and materials for 3D models from a text description. (Tool, Closed)
• Polycam: A phone and web app that turns photos, video or an iPhone's LiDAR scan into a 3D model, splat or floor plan. (Tool, Closed, free option)
• quso.ai: Turns a long video into short captioned clips for social media, with an editor that trims filler words and a scheduler that posts to seven networks. (Tool, Closed, free option)
• Qwen-Image: A free, downloadable model from Alibaba's Qwen team that turns descriptions into pictures and is especially good at writing text inside images, including Chinese. (Model, Fully open, free option)
• Rask AI: A web app that translates the speech in your videos into other languages, re-voices them in a copy of the original speaker's voice, and can match lip movements to the new audio. (Tool, Closed, free option)
• Real-ESRGAN: A free, open model that makes small or blurry photos bigger and sharper, with extra versions for anime. (Model, Fully open, free option)
• Recraft: A design-focused image maker in the browser and on phones. (Tool, Closed, free option)
• Remini: A phone app (also on the web) that sharpens old, blurry or low-resolution photos, especially faces, in one tap. (Tool, Closed, free option)
• remove.bg: Cuts the background out of a photo automatically in one step. (Tool, Closed, free option)
• Renderforest: An online studio for making videos, animations, logos and mockups from templates, now with AI tools that turn a description or picture into a video using several AI video models. (Tool, Closed, free option)
• Replicate: A pay-as-you-go service for running thousands of AI models by other makers, for pictures, video, speech, music and text. (Place to run it, Closed)
• Resemble AI: Used to offer voice cloning and text to speech, but has stopped selling voice generation. (Tool, Closed, free option)
• Respeecher: Makes your recorded voice sound like a different voice (speech-to-speech), or reads text aloud, using a library of ready-made voices. (Tool, Closed)
• Rev: Turns recordings into text using AI, or by paid human transcribers for higher accuracy. (Tool, Closed, free option)
• Revid AI: A browser tool for making short social videos (TikTok, Reels, Shorts) from an idea, a web link or a script. (Tool, Closed, free option)
• Riverside: A browser studio for recording podcasts and video interviews with remote guests in high quality, then editing them by editing the transcript. (Tool, Closed, free option)
• Rokoko Vision: Turns an uploaded video of someone moving into 3D character animation, free to try in your browser. (Tool, Closed, free option)
• Runpod: Rents graphics cards (GPUs) by the second so you can run AI models yourself, plus ready-made endpoints for popular image, video and speech models. (Place to run it, Closed)
• Runware: A pay-as-you-go service for developers that runs many makers' AI models through one API, mainly for pictures and video, plus some audio, 3D and text models. (Place to run it, Closed, free option)
• Runway: A browser studio for making short video clips from a description or a still image, and for editing video you already have. (Tool, Closed, free option)
• Runway Gen-4: Runway's video model that keeps the same character, object or place looking consistent across shots, guided by a reference image and a text description. (Model, Closed)
• RVC (Retrieval-based Voice Conversion): Free, downloadable software that makes a recording or live voice sound like another voice. (Model, Fully open, free option)
• SadTalker: A free, downloadable research model that makes a single portrait photo talk in time with an audio clip. (Model, Fully open, free option)
• Scenario: A web studio aimed at game and design teams. (Tool, Closed, free option)
• SeaArt: A website and phone app for making AI pictures and short videos from text or images, using many different models. (Tool, Closed, free option)
• Seedance: ByteDance's video model family. (Model, Closed)
• Seedream 4.0: ByteDance's picture model that both makes images from a description and edits existing ones by instruction, can combine several reference pictures, and outputs up to 4K. (Model, Closed)
• Sesame CSM: A free, downloadable speech model built to sound natural in back-and-forth conversation. (Model, Fully open, free option)
• Simli: A developer service for adding a live, talking video face to an app or website, such as a support agent or tutor that answers out loud. (Tool, Closed, free option)
• SkyReels V2: A downloadable video model from Skywork that makes clips from a description or a photo and can keep extending a clip to make much longer videos. (Model, Downloadable, with conditions, free option)
• Sloyd: A web app for making game-ready 3D models from a text prompt or a picture, then texturing, rigging and animating them. (Tool, Closed, free option)
• Sonix: Turns audio and video recordings into editable text transcripts in the browser, and can translate them and make subtitles. (Tool, Closed)
• Sora: OpenAI's app for making short video clips with sound from a written description, including putting yourself in scenes. (Tool, Closed, free option)
• Sora 2: OpenAI's video model that made short clips with matching speech and sound from a description or a still image. (Model, Closed)
• Soundful: Makes royalty-free instrumental tracks and beats from a chosen genre template, in your browser. (Tool, Closed, free option)
• SOUNDRAW: Makes backing tracks and beats in your browser: pick a genre, mood, length and energy, then tweak the result. (Tool, Closed, free option)
• Soundverse: A browser music studio that writes songs with vocals from a text prompt, and can also extend tracks, split songs into parts and clone a voice. (Tool, Closed, free option)
• Speechify: Reads documents, web pages and scanned text aloud in natural voices, mainly for studying and listening on the go. (Tool, Closed, free option)
• Splice: A big subscription library of royalty-free loops and samples made by people, with AI helpers that suggest matching sounds and build layered 'stacks' from a loop so you can sketch song ideas. (Tool, Closed)
• Spline AI: Part of the Spline 3D design app: type a sentence or upload a picture, choose one of four looks, and get a textured 3D model you can light, animate and put on a website or app. (Tool, Closed, free option)
• Stable Audio: Stability AI's browser app for making music and sound effects from a written description, or reworking audio you upload. (Tool, Closed, free option)
• Stable Audio 2.5: Stability AI's closed music and sound model. (Model, Closed, free option)
• Stable Audio Open 1.0: A downloadable model that turns a short English description into up to 47 seconds of stereo audio. (Model, Downloadable, with conditions, free option)
• Stable Diffusion 3.5: Stability AI's downloadable picture model that turns a description into an image, with better text and prompt-following than earlier versions. (Model, Downloadable, with conditions, free option)
• Stable Diffusion web UI (AUTOMATIC1111): A free, open-source program you install on your own computer to make and edit pictures with Stable Diffusion models, through a page in your browser. (Tool, Fully open, free option)
• Stable Diffusion XL 1.0: Stability AI's 2023 open image model that turns a description into a picture. (Model, Downloadable, with conditions, free option)
• Stable Fast 3D: Stability AI's downloadable model that turns one photo of an object into a textured, low-poly 3D model in about a second. (Model, Downloadable, with conditions, free option)
• Stable Point Aware 3D (SPAR3D): Stability AI's downloadable model that builds a textured 3D model from one picture in about a second. (Model, Downloadable, with conditions, free option)
• Stable Video Diffusion: A downloadable model from Stability AI that turns one still picture into a very short clip of a few seconds. (Model, Downloadable, with conditions, free option)
• starryai: A phone and browser app that turns a description into a picture in many art styles, and can restyle, enlarge or cut out photos. (Tool, Closed, free option)
• Step1X-3D: StepFun's open 3D model maker: it turns one picture into a clean 3D shape, then paints a texture onto it. (Model, Fully open, free option)
• Steve AI: Turns a script, blog post or idea into an animated or stock-footage video, with cartoon characters, AI presenters and computer voices. (Tool, Closed, free option)
• Stockimg AI: Makes ready-to-use graphics from a description: logos, posters, illustrations, stock-style photos, wallpapers and social posts, with simple editing and social scheduling. (Tool, Closed, free option)
• Submagic: Adds animated captions and quick edits to short videos for social media, and can cut longer videos into short clips. (Tool, Closed, free option)
• Suno: Makes complete songs, with singing, from a short description or your own lyrics, in a browser or phone app. (Tool, Closed, free option)
• sync.: A lip-sync service: give it a video and new speech, and it changes the speaker's mouth to match. (Tool, Closed, free option)
• Synthesia: Turns a script into a video with a digital presenter, mainly for training and business videos. (Tool, Closed, free option)
• Synthesys: A browser studio for making video adverts and explainer videos from a brief, a web link or your own footage, with stock AI presenters, AI voiceover, images and short AI clips. (Tool, Closed)
• Tavus: Builds AI video presenters, mostly for developers: a lifelike face you can hold a live video conversation with, or videos read from a script. (Tool, Closed, free option)
• Tensor.Art: A community website where people share AI image models and styles and run them in the browser to make pictures. (Tool, Closed, free option)
• Together AI: A pay-as-you-go cloud service, mainly for developers, that runs many other makers' AI models: chat and code models, plus picture and video models such as FLUX, Seedream and Kling. (Place to run it, Closed)
• Topaz Gigapixel: A Mac and Windows app that uses AI to enlarge photos (up to 6x) while keeping them sharp, and to repair low-quality images and faces. (Tool, Closed)
• Topaz Photo: A desktop app for Mac and Windows that uses AI to sharpen, de-noise, enlarge and repair photos, including blurry faces, dust and scratches. (Tool, Closed)
• Topaz Video: Desktop software (Mac and Windows) that cleans up and sharpens existing video: upscaling old or low-quality footage to 4K, removing noise, steadying shaky shots and adding frames for smooth slow motion. (Tool, Closed)
• TopView: Makes marketing and product videos, including AI presenters that hold or show your product, lip-sync, and voice clones. (Tool, Closed)
• TRELLIS: Microsoft's free, downloadable model that turns a picture (or, less well, a text prompt) into a textured 3D model you can save as a GLB file. (Model, Fully open, free option)
• Tripo AI: Turns a text description or one or more pictures into a 3D model in your browser, then can texture it, split it into parts and rig characters for animation. (Tool, Closed, free option)
• TripoSR: A free, open model from Tripo AI and Stability AI that guesses a rough 3D shape from a single picture in under a second on a strong graphics card. (Model, Fully open, free option)
• Typecast: Type a script and pick from a library of AI voices to have it read aloud with adjustable emotion, or turn it into a talking-avatar video. (Tool, Closed, free option)
• Udio: Makes songs, including singing, from a text description, and can extend or remix audio you upload. (Tool, Closed, free option)
• Ultimate Vocal Remover: A free desktop app that splits a song into parts, such as vocals and instruments, on your own computer. (Tool, Fully open, free option)
• Upscayl: A free, open-source desktop app that makes small or blurry pictures bigger and sharper using AI. (Tool, Fully open, free option)
• Vectorizer.AI: A website that turns a normal picture such as a logo or drawing (PNG, JPG) into vector artwork you can scale to any size, as SVG, PDF, EPS or DXF. (Tool, Closed, free option)
• VEED: An online video editor aimed at social media. (Tool, Closed, free option)
• Veo 3: Google's video model that turns a description or a still image into a short clip (usually 8 seconds) with sound, including speech. (Model, Closed)
• Videoleap: A phone and browser video editor from Lightricks with AI extras: turning text into video, AI effects and templates, background and object removal, auto subtitles and image generation. (Tool, Closed)
• Vidnoz AI: A browser tool for making presenter videos from a script with stock AI avatars, making a photo talk, cloning your voice and translating videos with lip-sync. (Tool, Closed, free option)
• Vidu: A web and phone app for making short video clips from a description, a photo, or several reference pictures that keep the same characters or objects. (Tool, Closed)
• Viggle: Puts a character from a picture into a video, copying the movement of the person in the clip, or swaps characters live. (Tool, Closed, free option)
• Vizard: Turns a long video into short vertical clips for TikTok, Reels and Shorts. (Tool, Closed, free option)
• Vizcom: A design tool for product and industrial designers that turns rough sketches into realistic renders, and can also make simple 3D models and short animations from them. (Tool, Closed, free option)
• Voice-Swap: A web studio for turning a sung or spoken recording into another voice from its library, splitting songs into parts, and reading text aloud. (Tool, Closed)
• Voicemaker: A browser text-to-speech tool: paste text, pick from a library of voices and languages, and download the narration as an audio file. (Tool, Closed, free option)
• Voicemod: A free app that changes how your voice sounds in real time while you chat, stream or play games, with 200+ voices and sound effects. (Tool, Closed, free option)
• Vozo: Translates and dubs videos into other languages, can match lip movements to the new audio, and translates subtitles and on-screen text. (Tool, Closed, free option)
• Vyond: A browser app for making animated explainer and training videos with cartoon-style characters, AI presenters and text-to-speech voices. (Tool, Closed)
• Wan 2.1: A free, downloadable video model from Alibaba's Wan team. (Model, Fully open, free option)
• Wan 2.2: A free, downloadable video model from the Wan team. (Model, Fully open, free option)
• Wav2Lip: An older, free research model that makes the lips in any video match a new audio track. (Model, Downloadable, with conditions, free option)
• WaveSpeedAI: A pay-as-you-go service for running many makers' AI models: video (Seedance, Wan, Kling, Veo and others), images, speech and music, lip-sync avatars and 3D. (Place to run it, Closed, free option)
• WellSaid Labs: A text-to-speech studio for business voiceovers such as training videos and adverts. (Tool, Closed, free option)
• Whisper: A free speech-recognition model from OpenAI that turns recordings into text in many languages and can translate speech into English text. (Model, Fully open, free option)
• Wisecut: A browser video editor that trims long talking videos automatically: it cuts silences, adds captions and background music, reframes for phones and pulls out short highlight clips you can schedule to social media. (Tool, Closed, free option)
• Wondershare Virbo: Wondershare's app for making presenter videos: pick an AI avatar and voice, type a script or paste a product link, and it makes a talking-presenter video. (Tool, Closed, free option)
• XTTS-v2: A downloadable text-to-speech model that reads text aloud in 17 languages and can copy a voice from a 6-second clip. (Model, Downloadable, with conditions, free option)
• YuE: A free, downloadable model that turns your lyrics and a style description into a full song with singing and backing music, in English, Chinese, Japanese, Korean and more. (Model, Downloadable, with conditions, free option)
• Zebracat: Turns a prompt, script or blog post into a finished short video with AI clips, stock footage, a voiceover and captions. (Tool, Closed, free option)