All integrations

JigsawStack

AI · AI

Web search, AI scraping, speech to text, translation, and OCR on their own key.

Acts as the person, not as itself

Each user connects their own account. Every call carries both identities — the agent and the person it is acting for — so the agent can never reach past what that individual can already do.

Credentials never touch the agent

Tokens live in the vault and attach server-side at call time. The agent holds a session, not a secret, and revoking access does not mean rotating a key.

Every call on the record

Who asked, which agent acted, which action ran, and the verdict that let it through — one audit trail across every integration, not one per vendor.

What an agent can do

Each action is granted on its own. An agent allowed to read is not thereby allowed to write, and the scope beside each row is what the acting user must have connected for it to run at all.

jigsawstack_delete_ai_tts_clone_by_voice_idWRITE

Remove a cloned voice from the account by its voice id. JigsawStack publishes no reference page for its text-to-speech routes, so this description is written from the route rather than quoted from one; the route itself is live and takes no body.

api
jigsawstack_delete_prompt_engine_by_idWRITE

Delete a prompt engine.

api
jigsawstack_delete_store_file_read_by_keyWRITE

Delete a file from JigsawStack file storage.

api
jigsawstack_get_ai_sentimentREAD

Perform line by line sentiment analysis on any text with detailed emotion detection. This is the query-string form of the same operation POST /ai/sentiment performs with a JSON body.

api
jigsawstack_get_ai_tts_cloneREAD

List the cloned voices on the account. JigsawStack publishes no reference page for its text-to-speech routes, so this description is written from the route rather than quoted from one. Note the measured quirk on this route: it is the only GET on the API that requires a Content-Type header, and this integration sends it.

api
jigsawstack_get_pingREAD

Reach the API and confirm the connection's credential is accepted. JigsawStack publishes no reference page for this route; it is the cheapest authenticated call the contract declares, which is why it is also what the connect-time probe uses.

api
jigsawstack_get_prompt_engineREAD

List all prompts in your project.

api
jigsawstack_get_prompt_engine_by_idREAD

Retrieve the details of a stored prompt.

api
jigsawstack_get_web_search_suggestREAD

Get suggestions for a given query in real time.

api
jigsawstack_head_store_file_read_by_keyREAD

Check whether a file exists in JigsawStack file storage without downloading it. A HEAD returns no body at all: success IS the answer, and a missing key is an error carrying the provider's status.

api
jigsawstack_post_ai_image_generationREAD

Generate an image from a text prompt using models such as Flux and Stable Diffusion.

api
jigsawstack_post_ai_predictionREAD

Forecast a wide range of time series data in seconds with one simple API and no data training.

api
jigsawstack_post_ai_scrapeREAD

Scrape any website instantly and get consistent structured data in seconds without writing any CSS selector code.

api
jigsawstack_post_ai_sentimentREAD

Perform line by line sentiment analysis on any text with detailed emotion detection.

api
jigsawstack_post_ai_sqlREAD

Convert natural language to an SQL query for a named database dialect. Supplying the schema, or the key of a schema stored on JigsawStack, makes the generated query match real tables.

api
jigsawstack_post_ai_transcribeREAD

Transcribe video and audio files with ease leveraging the Whisper large V3 AI model. Supplying `webhook_url` makes the call asynchronous: JigsawStack answers immediately and posts the transcript to that URL when it is done.

api
jigsawstack_post_ai_translateREAD

Translate text from one language to another with support for multiple text formats.

api
jigsawstack_post_ai_translate_imageREAD

Extract and translate text from images into multiple languages.

api
jigsawstack_post_classificationREAD

Classify text and image datasets using custom labels.

api
jigsawstack_post_embeddingREAD

Generate vector embeddings from various content types including text, images, audio and PDF files, with speaker fingerprint support.

api
jigsawstack_post_object_detectionREAD

Recognise objects within an image with great accuracy.

api
jigsawstack_post_prompt_engineWRITE

Create a prompt for easy reuse.

api
jigsawstack_post_prompt_engine_by_idREAD

Execute a stored prompt engine by its id, filling its declared inputs from `input_values`.

api
jigsawstack_post_prompt_engine_runREAD

Run a prompt directly, without storing it first. Takes the same prompt definition `create_prompt` stores, plus the input values to fill it with, and returns the result in one call.

api
jigsawstack_post_validate_nsfwREAD

Quickly detect nudity, violence, hentai, porn and more NSFW content in images.

api
jigsawstack_post_validate_profanityREAD

Check any text for profanity.

api
jigsawstack_post_validate_spam_checkREAD

Perform spam check analysis on a given text in seconds.

api
jigsawstack_post_validate_spell_checkREAD

Check and correct spelling errors in a text.

api
jigsawstack_post_vocrREAD

Recognise, describe and retrieve data within an image with great accuracy.

api
jigsawstack_post_web_deep_researchREAD

Effortlessly run deep research and get high-quality results powered with AI.

api
jigsawstack_post_web_html_to_anyREAD

Capture screenshots of a website, convert HTML to both image and PDF formats.

api
jigsawstack_post_web_searchREAD

Effortlessly search the Web and get access to high-quality results powered with AI.

api

Put JigsawStack behind one governed endpoint.

Same permissions, same audit trail, whatever else you connect next.