API Tools

Clicking the links below will open the listed AI tools in new tabs in your browser. The list includes API tools for research, analysis, writing, grading, media and other educational uses. You can find agents and browser extensions on the models page. I would start with the tools in bold.

APIs = APPLICATION PROGRAM INTERFACE. This is a huge category and most of the new products you see are here using an API to interact with one of the frontier models for you. You can often replicate the results with longer and careful prompting, but these are very useful shortcuts. 

APIs for INFORMATION, LITERATURE SEARCH & RESEARCH

  • Undermind.ai is free with an edu account and it does deep research to do a scholarly lit review report which you can then interrogate. It includes links and summaries as well as a score for how closely the article aligns with your research question.
  • Consensus.app and Elicit.com are academic research tools that limit data search to the 200M published papers in Semantic Scholar and use AI (ChatGPT) to allow you to filter by claims, methodology, sample size and more. Consensus includes a “consensus meter” that provides an estimate of the consensus in the published literature. Here is the result when asking “do brain games work?” Elicit has a filter that allows you to search by the quality of journal.
  • Storm (short for brainstorm) is a new research tool from Stanford that creates a Wikipedia-like report on the topic of your choice. It looks at more than just Semantic Scholar publications. It will write/summarize from different perspectives (ex. sociologist vs political scientist) and tell you what sources it used. Compare the results and format with what you get from Consensus. 
  • FutureHouse is a collection of tools for scientific discovery. The “Owl” tool, for example, doesa “precedent search” (has someone already done this?) and “Phoenix” which is an agent that uses cheminformatics tools to do chemistry and can plan synthesis and design new molecules. You can watch a demo here.
  • Perplexity.ai was designed as an AI-powered chatbot search engine (the first but now also Dia and Gemini and Comet with the Perplexity browser). It is most flexible for the type of web search you want–academic, social, financial etc. It answers your questions with the sources cited using multiple frontier models. Perplexity also has an Internal Knowledge Search that will search your files for info and many other useful tools.
  • Here is a comparison of Consensus, Elicit, Storm and Perplexity answering the question “do polls predict elections?”
  • Compare these to Google’s LearnAbout.
  • Researchrabbit and Litmaps are both more visual, showing you a network of articles that relate to a topic. It is a bit like Spotify for research papers (you liked that, you should know about this).
  • SciSpace also has similar functions but with a broader suite of tools, like a paraphraser that rewrites or helps explain passages (something you can also find in ExplainPaper.) All four of these are essential lit review tools. 
  • Scite extracts citations and uses AI to analyze if they are cited with support or contradiction in other papers. Upload a pdf or your citations and find out quickly about the impact of the work.
  • Semantic Scholar a free AI search tool with a pdf reader.
  • DeepResearch (available only with Gemini Advanced) creates a multi-step research plan. If you approve, it searches the web, analyzing relevant information. It repeats this process multiple times to generate a report of the key findings with links (which you can export into a Google Doc). The difference from the other research tools is this is agenic: it searches the web and repeats the process. 

APIs for ANALYSIS, & WORKING with DATA. Here is a subcategory of tools that allow you to control the data set or knowledge base:

  • NotebookLM is Googles version of a research assistant but it works only on the documents (up to 50) you upload (up to 500,000 words EACH). Use it as a virtual committee assistant: link or upload all of your institution policy documents plus the committee charge and then faculty can interrogate s needed. Try uploading a pdf (or 50) and asking for a study guide or an interactive mind map or podcast (you can interrupt to ask questions). Here is an AI-created podcast about the first part of my Teaching Change book. If you upload files to Gemini, you will see a “Generate Audio Overview” button appear which also creates a podcast summary.
  • Mem has similar features that allow you to “chat with your data.” Perplexity calls its version of this Spaces.
  • There are lots of “chat with your data” sites that pitch themselves as “research” tools, but are really aimed at students. Sites like Scholarcy, Mindgrasp (“Learn 10x faster!”) and CoralAI, (“read documents faster”) focus on summaries and audio transcriptions (like lectures you did not attend). 
  • Dia is a new AI browser that allows you to chat with websites (or all of your tabs at once), so students are using it a lot to summarize and ask questions directly in an LMS or course documents. For example, a student could open all courses and then create a master calendar for deadlines or create a study guide from all of the slides. Yes, this could be done in NotebookLM by uploading all of the files, but this allows this just by looking at webpages.
  • The tech behind the podcast feature in NotebookLM is Illuminate, which has more features: you can change the voices, accents or styles and turn any content or webpage into a dialogue. A competitor is GenFM from ElevenLabs.

APIs for GRAPHICS, CHARTS and VISUALS

  • Napkin creates infographics and visualizations from your text. You don’t have to prompt–just drop in the items you want to visualize and you get lots of options that you can then alter with easy tools.
  • MyLens creates editable visuals from text, PDFs, videos, webpages or spreadsheets. (Data is not used for model training.) You can choose from timetable, mind map, table, flowchart or other kinds of graphics.
  • Nomic Atlas îs best for analysis of huge unstructured data sets and does a range of visualizations.
  • Julius also allows you to do computations and visualizations with your data and also writes reports, finds insights and does analysis.
  • Ailyze is focused on qualitative data and insights and also has an AI-driven interviewer to help with collecting data.
  • Infography also makes infographics from text.

APIs for WRITING, GRADING, TUTORS and MORE

  • WRITING: Grammarly, and Quillbot are already known to students (before they were enhanced with AI) and (along with the newer Caktus) blur the line of improving with cheating, offering to write paragraphs, solve problems, answer questions and check if your content can bypass AI detectors. Try Lex first for your own writing. NotionAI, Copy.ai and Jasper and many many others focus on specific types of writing or business uses.

  • GRADING: Your choice here is either to use one of the best (smartest) frontier models (see above) but understand that is is naive and you will need to provide lots of very specific instructions (it needs a recipe) or you can use one of these already fine-tuned models (that already knows how to cook) that often use and older, cheaper and less smart (GPT 3.5) to do the work. There are already over 70 AI grading tools available.
    • GradeWiz extracts students names before grading and then sends anonymous essays to multiple AIs and then compares the results.
    • CoGrader does general grading and feedback and integrates with Google classroom. Try the 2.0 version here: https://v2.cograder.com/
    • TimelyGrader can import assignments from your LMS and export grades back to it.
    • AI For Teachers: Free for ChatGPT Plus users
    • Gradescope: Also from Turnitin.
    • Kangaroos AI: Customizable rubrics and bulk uploads.
    • EssayGrader: Free option (with limited rubric customization) and allows bulk uploading.
    • Smodin: Limited free version but includes language translation.
    • GradeCam: Instant feedback that integrates with some LMS.
    • SnapGrader: Includes a scanning feature. 
  • ChatBot Assignments with Grading: Mostly K-12 at the moment, but look for new platforms like Parlay and Mizou that create specialized chatbots for problems or situations and then grade student interactions–all within a protected environment.

  • NOTE-TAKING: Microsoft OneNote, Otter.ai, Fireflies, and Zoom Companion all do more than just transcribe notes, organize and summarize (often across multiple documents/meeting ). They can analyze who is talking (or interrupting) the most and some even the emotions of participants. Find the latest list of “best” on your platform. We are now starting to see meeting note taking combined with agent tools so SpinachAI creates action items on Attio, HubSpot, Salesforce, or Zoho, sends customers status updates and creates documentation in Google Docs (all in 100 languages).

  • STUDY ASSISTANTS: Both Nurovant, Turbolearn.ai and GradeMaxx (and MANY more) can turn lecture notes, a pdf, a phone recording or a YouTube video into an outline, practice tests, flashcards, mind maps, quizzes or notes. Learn About is hoping to be a big player in this space.
  • NotebookLM also does this: try uploading notes, pdf (or up to 50 documents of content) and it will create a summary, sample questions, study guide or even a podcast: here is an AI-created podcast about the first part of my Teaching Change book. (What about an assignment that asks students what information is missing?)
  • Storm is a new research tool from Stanford that creates a Wikipedia-like report on the topic of your choice. 
  • There are a growing number of more visual ways to explore new topics and all of these create concept maps (and each does more):  Mapify, Albus, and Heuristica(which also has templates for pro/con boxes, controversial points, flash cards and more).
  • Caktus is popular with students because it bills itself as a study assistant, but its top tools include an essay writer, a humanizer, an AI detector bypass tool, a math solver, and a discussion responder (designed for discussion boards). Oh, and a life coach…

VOICE AND DIALOGUE: (More on voice and video clones below.)

  • Hume.ai both understands your emotions and the emotions in what it is saying.
  • Sesame has a very natural sounding voice to voice conversational style and I prefer it for practicing conversations.
  • GPT 4o added Live Mode in its Advanced Voice Mode in May 2024. Claude and Gemini can also talk to you now live. Ask it to create a customized bedtime story. Watch some of the videos to get a sense of how seeing and hearing (and interrupting) might be leveraged as a tutor or for translation.
  • The engine behind the podcast feature in NotebookLM is ElevenLabs, which offers more customization options but also does other text to audio conversions
  • Resemble AI also has a no-cost, open-source model called Chatterbox that can clone any voice using just five seconds of audio and can try it here.)
  • Here is a comparison of several models including the new Dia from NariLabs 
  • Amazon Nova Sonic says it understand both what you say and how you say it.
  • Kokoro is an open-source model that also allows you to create natural sounding speech from text.
  • Octave (from Hume) does this text to speech but understands what it says so can add emotions…
  • Scribe gives you speech to text in 99 languages.

  • LANGUAGE LEARNING: Duolingo was first out of the gate with Duolingo Max, but you can, of course, have a conversation with ChatGPT or other AI in voice mode) in another language and ask it to correct your usage and pronunciation. (You do need to prompt it with something like “help me practice conversations in language X, correct me if I’m make a mistake and explain why.” Not also that many of the regional models above are more native speakers, which might also enhance cultural knowledge. There are also a slate of immersive language tools like Langua (more engaging than Duolingo), Glossarie, Speak, TalkPal and Tutor Lily (not the same as Duolingo’s Lily) which allows you to change the speed of the voice tutor. Univerbal combines text and audio, although audio only mode is probably better for real conversation.  Mondly VR and ImmerseMe add an immersive VR element. Speakable bills itself as your all-in-one language TA.
  • Try DeepL for translations, although Google Translate remains the standard.
  • LingoSub adds subtitles in any language to videos (allowing you to practice new languages).
  • Note that Google Meet now includes real-time language translation.

IMAGES, SLIDES, VIDEO, MUSIC and more Multimodal AI can both create and analyze sound, pictures and video. Vertex AI allows you to use all of the Google creative models (Lyria for music, Veo for video, Imagen for images, Chirp for voice and a new Flow tool to create longer video) all in one place.

  • IMAGES: The easiest and maybe best way to make images (since about the middle of April 2025) is natively in ChatGPT and Gemini -CoPilot and Meta also do this). This means the LLM directly controls the image making and it means your prompts can be more subtle. (Try making an infographic for a complicated topic: the LLM can now both work out the concepts and put them into an image.) This also means that you need to. upgrade to a paid model, since the quality of the image depends on the quality of the model (so GPT-4o is the better image generator.) Note that in the general models, you need to include the stylistic prompts yourself (do you want a wide-angle realistic photo or a cubist painting? In other words–the words used to describe visual images and video are important knowledge for the user!) Ask for an image and then add an object or change your background or hair color (“don’t change anything else”). In ChatGPT you can also upload a reference image or a color palette. You can see the current leaderboard of text to image models here.
  • Imagen4 from DeepMind is one of the best image generators and you can now use it either in ImageFX (also Google) or in Gemini directly. Either for free.
  • Seedance from Chinese ByteDance and the API version Seedream 3.0 are strong contenders. You can see a comparison here,
  • Ideogram 3 is a very solid free image generator.
  • Adobe Firefly allows you to use both its own models (trained exclusively on commercially safe content–i.e. they paid artists for the work that the model was trained on) with further access to Google, OpenAI, and Black Forest Labs. Model 4 is quicker but Ultra is better. Firefly Boards can do “hundreds of variations at once.”
  • Krea offers a range of visual AI tools that do graphics, logos and images. Krea 1 says it avoids the “AI look.” You can see a test here, and indeed if you are creating humans this has a more
  • Higgsfield has a “high-aesthetic photo model” full of visual effects just for Soul for fashion work…
  • Image Creator from Microsoft Designer still provides free access to the latest goodies in Dalle3.
  • Tess Design was trained on licensed art and allows artists to create and control their own style.
  • Whisk allows you to use images as prompts for new images.
  • Komiko creates comics, manga and other animations.
  • Reve is a bit hit or miss for me.
  • DALL-E by OpenAI (but not free for the best model)
  • Runway (based on Gemini): Note this new Act-1 feature that allows you to control animation with your own facial expressions.
  • HART: Efficient Visual Generation with Hybrid Autoregressive Transformer is a free and super fast image generator from MIT that also uses less computing power.
  • Stable Diffusion is good, cheap and open source
  • Midjourney is one of the best but can only be used through Discord.
  • Generative AI by Getty Images creates stock images

  • VIDEO: The “best” model for video is shifting every week at the moment but here is great guide (with comparisons you can watch) of the top AI video tools.
  • Veo 3 (from DeepMind) and currently free in Google AI Studio is currently the best, and includes sound creation (dialogue). See great examples here. Vertex AI allows you to use all of the Google creative models.
  • Kling (from China’s Kuaishou Technology). Kling 2.1 is cheaper and close to Veo 3. It depends on which comparison you watch. Here is another more detailed comparison.
  • Seedance from Chinese ByteDance.
  • Sora (from OpenAI with ChatGPT Plus). You can use this in ChatGPT but Sora gives you a set of dropdown “presets” which can be useful if you do not already understand the language of art history, image and video styles. In Sora you can also open a present (like Film Noir or Balloon World) which will show you the instructions/preset prompt which you can then customize. You can also upload images you want to use for inspiration with the “attache media” button.
  • LTX from Lighttricks says it is the most powerful open-source video generator and can produce video faster than you can watch it…
  • Runway (based on Gemini). Gen4 is excellent but not free
  • Hailuo from MiniMax has impressed lots of folks and it is free for now.
  • ByteDance’s Seedance 1.0 is ranked ahead of Veo 3 in some benchmarks.
  • Higgsfield has lots of cool motion control effects that allow you to do camera angles like overhead sweeps.
  • Flux
  • Krea
  • Movie Gen (from Meta) 
  • Hedra 3 is very good.
  • Pika also allows you to make a video with your younger self…
  • HunyuanVideo from Tencent in China.
  • Genie 2 converts images into interactive virtual worlds/games.
  • Guidde can turn a pdf, slide deck or screen cast into a “how to” video in multiple languages.

  • MUSIC/SONGS: Suno will convert your instructions into a new song. As always more specific instructions yield better results, and not that the real benefit is that you can customize for specific people and events. (Try creating a gratitude song for a friend in a style they like with the details of what they did.) Udio and Producer (formerly Riffusion) also do this–and I think Producer has a little more complexity to it. ElevenLabs also now does music (with a workshop-created sample here.) You can also use Lyria in the Google Studio, which also has a “live” mode for jamming in real time. Think about how you could customize walk-on music for your class. Here is an example from Prof. Martin’s Service Management class sat the University of South Carolina.

  • AVATARS and VOICE CLONES: HeyGen was first but Synthesia and Colossyan also do both video and voice clones. Canva has a limited avatar maker. (You can now also send an avatar to a Zoom meeting.) HeyGen also allows you to add a knowledge base to an interactive avatar (think you as a TA) and its Avatar IV will generate a lip-synced avatar from a photo and a script. It also has Sora2 built in which opens huge possibilities.
  • LHM from Alibaba provides a way to turn a full-body image into a 3D avatar.
  • You can create a voice clone with a few seconds of your voice in ElevenLabs, Cartesia, Hume.ai, Sesame, MiniMax, Higgsfield, Inworld, Chatterbox, Kukarella, Lalal, OpenVoice and Resemble. All offer a range of ways to turn text into audio using your voice or someone else’s.
  • Most of these models offer some protections (Hume is HIPPA compliant) but also have a default that they can use what you do for training. You need to check and opt out to retain your rights.
  • There are also open-source code versions of ChatterBox and OpenVoice available for downline on GitHub. This allows you to do voice clones entirely OFFLINE–so on your computer without sending any data to a company’s server.
  • Here is an old review of ten voice cloners.