Version: 2.0

AI Builder API

The AI Builder API turns a natural-language prompt into a Prezent-quality deck, lets you revise it by describing the change you want, and hands you the finished file.

All three operations stream. You start the work, then read Server-Sent Events for progress and the result — there is no status endpoint to poll.

Full schemas and per-field documentation live in the interactive API Reference.

Coming from API 1.0?

The AI Builder API changed substantially in 2.0 — polling became streaming, and the many editing endpoints collapsed into one. See What changed from 1.0 below. The 1.0 API is unchanged and still served; its docs are under version 1.0.

Authentication

All endpoints require a Bearer token:

Authorization: Bearer YOUR_API_KEY

See Getting Started → Authentication for details.

Endpoint summary

Method	Path	Description
`POST`	`/api/v2/generate`	Generate a presentation
`POST`	`/api/v2/autogenerator/edit`	Revise a presentation
`POST`	`/api/v2/autogenerator/download`	Download the file
`POST`	`/api/v2/streams/sessions`	Get a stream URL for a `callback_id`
`GET`	`/api/v1/autogenerator/templates`	List available templates
`GET`	`/api/v2/autogenerator/languages`	List supported languages
`GET`	`/api/v2/integrations/auth`	Connect a third-party app
`GET`	`/api/v2/integrations/auth/status`	Check an app's connection

GET /api/v1/autogenerator/templates keeps its v1 path — it is unchanged in 2.0 and there is no v2 equivalent.

How the streaming flow works

Generate and edit both follow the same three steps:

1. POST /api/v2/generate            →  { resData: { callback_id } }
2. POST /api/v2/streams/sessions    →  { data: { stream_url } }
   with that callback_id
3. open stream_url  (SSE)           →  progress events…
                                       terminal event + download_url

Download is two steps, not three — POST /api/v2/autogenerator/download returns a stream_url directly, so it skips step 2.

The event contract

Every event on a v2 stream has the same shape, so one parser handles the whole stream:

event: status
data: {"status":"inprogress","message":"Analyzing the key elements","callback_id":"3f8e7d61-…"}

Field	Notes
`status`	`inprogress` while working; then one of `success`, `failed`, `cancelled`
`message`	Human-readable step description — safe to show a user verbatim
`callback_id`	The generation or edit turn this event belongs to
`download_url`	Only on a `success` event. May be `null` on a generation stream if the file has not been exported yet

The stream closes after the terminal event. Branch on status rather than on the SSE event: name — it carries the same information and is simpler.

Progress messages are drawn from a fixed set, in order:

Understanding your prompt
Checking for app references — only when the prompt references a connected app
Analyzing the key elements
Adjusting structure for clarity
Optimizing spacing and alignment
Crafting your speaker notes — only when notes were requested
Finalizing your slides

Steps that do not apply are skipped, so do not treat this as a fixed-length progress bar.

Reconnection, timeouts, and full client code are in Streaming (SSE).

Response envelopes

Errors use the canonical envelope on every endpoint:

{ "success": false, "data": null, "error": { "code": "...", "message": "..." } }

Success shapes are not uniform — each endpoint documents its own:

Endpoint	Success shape
`POST /api/v2/generate`	`{ message, resData, error }`
`POST /api/v2/autogenerator/edit`	`{ message, resData, error }`
`POST /api/v2/autogenerator/download`	flat top-level fields
`POST /api/v2/streams/sessions`	`{ success, data }`
`GET /api/v2/autogenerator/languages`	`{ status, message, data }`
`GET /api/v1/autogenerator/templates`	`{ success, data }`
`GET /api/v2/integrations/auth`	one of two shapes — see the endpoint

See Developer Guide → Error codes for the full code catalog.

`POST /api/v2/generate` — Generate a presentation

Starts a generation and returns a callback_id. Nothing else — the deck arrives over the stream.

Request body

Field	Type	Required	Description
`prompt`	string	yes	What to generate, in plain language.
`template_id`	string	no	Brand template to apply. Takes precedence over `settings.template_id`; falls back to your key's configured template.
`audience_id`	string	no	Audience profile to tailor tone and detail to. See Audiences.
`audience`	object	no	Object form, `{ "id": "…" }`. `audience_id` takes precedence.
`files`	array	no	`[{ "file_id": "…" }]` — files to ground the deck in. Upload first via `POST /api/v1/preprocess`.
`web_links`	array	no	URLs for the generator to read.
`text`	string	no	A block of text as source material.
`texts`	array	no	Several blocks of text. Takes precedence over `text`.
`websearch`	boolean	no	Let the generator search the web. Takes precedence over `settings.websearch`. Default `false`.
`externalContext`	boolean	no	Alias for `websearch`.
`settings`	object	no	Generation settings — see below.

Be specific in the prompt. "A 10-slide deck on renewable-energy market trends for a board audience" produces a better result than "renewable energy".

Settings

Every key in settings is optional. An omitted key falls back to the default configured on your API key, then to the documented default — so a fully configured key needs no settings object at all.

Key	Type	Accepted values / default
`template_id`	string	Any template you can access. Root `template_id` wins.
`language`	string	A `locale` from `/api/v2/autogenerator/languages`. Default `en`.
`websearch`	boolean	Default `false`. Also settable at the root of the request, which takes precedence.
`add_sources_to_footer`	boolean	Default `false`.
`add_sources_to_slides_note`	boolean	Default `false`. Takes precedence over `add_speaker_notes_to_slides_note`.
`generate_speaker_notes`	boolean	Default `false`.
`add_speaker_notes_to_slides_note`	boolean	Default `false`. Ignored when `add_sources_to_slides_note` is enabled.
`image_library`	object	`{ brand_library, prezent_library, ai_images, my_workspace, additional_context }`, each a boolean. Omitted keys default to `false`, except `ai_images`, which defaults to `true` when `image_library` itself is omitted. `company_library` and `brand_library` are the same library — set `brand_library`.
`voice_settings`	object	`{ "type": "standard" }` — brand-voice profile.
`deck_default_size`	integer	1–200, default `7`. The prompt can override it.
`deck_max_size`	integer	1–200, default `100`. Must be ≥ `deck_default_size`.
`export_type`	string	`pptx` or `pdf`. Default `pptx`.
`enable_mcp_context`	boolean	Default `false`. Pull context from connected apps.

Example

cURL
Python
Node.js

curl -X POST https://api.prezent.ai/api/v2/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A 10-slide deck on renewable-energy market trends for 2026",
    "template_id": "your-template-id",
    "settings": {
      "language": "en",
      "websearch": true,
      "generate_speaker_notes": true
    }
  }'

import requests

resp = requests.post(
    "https://api.prezent.ai/api/v2/generate",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "prompt": "A 10-slide deck on renewable-energy market trends for 2026",
        "template_id": "your-template-id",
        "settings": {
            "language": "en",
            "websearch": True,
            "generate_speaker_notes": True,
        },
    },
)
resp.raise_for_status()
callback_id = resp.json()["resData"]["callback_id"]

const res = await fetch('https://api.prezent.ai/api/v2/generate', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    prompt: 'A 10-slide deck on renewable-energy market trends for 2026',
    template_id: 'your-template-id',
    settings: { language: 'en', websearch: true, generate_speaker_notes: true },
  }),
});

const { resData } = await res.json();
const callbackId = resData.callback_id;

Success response (`200`)

{
  "message": "Job submitted successfully",
  "resData": {
    "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91"
  },
  "error": null
}

The payload is under resData, not data.

callback_id is valid for about 3 hours and is what you pass to streams, edit, and download.

Validation errors (`422`)

Field-level failures return INVALID_INPUT with error.details as an array of messages, one per failed field:

{
  "success": false,
  "data": null,
  "error": {
    "code": "INVALID_INPUT",
    "message": "The request contains invalid input.",
    "details": [
      "prompt is required",
      "settings.language: 'xx' is not a supported language locale"
    ]
  }
}

`POST /api/v2/autogenerator/edit` — Revise a presentation

Applies a natural-language edit. One endpoint replaces 1.0's regenerate, node-change, and slide-actions — describe the change instead of choosing an operation.

Edits are conversational: each builds on the last. Pass the callback_id of the most recent turn, and use the new id you get back for the next edit.

The generation must have finished

A slide can only be addressed once the deck size is known, so editing a callback_id that is still generating returns 400. Wait for the stream's terminal event first.

Only one turn runs at a time — if a previous edit is still in flight, the request is rejected with that reason in error.message.

Request body

Field	Type	Required	Description
`callback_id`	string	yes	The presentation to edit — the id of the original generation, or of the most recent edit.
`prompt`	string	yes	The change to make, in plain language.
`slideIndex`	integer	no	Which slide to edit, counting from 0. Omit to edit the whole deck.
`files`	array	no	`[{ "file_id": "…" }]` — context for this edit.
`web_links`	array	no	URLs to read as context.
`text`	string	no	A block of text as context.

slideIndex is validated against the actual deck — a value past the last slide returns 400 reporting the real slide count.

Example

# Edit the whole deck
curl -X POST https://api.prezent.ai/api/v2/autogenerator/edit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91",
    "prompt": "Make the tone more formal and shorten every bullet"
  }'

# Edit slide 5 (index 4)
curl -X POST https://api.prezent.ai/api/v2/autogenerator/edit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91",
    "prompt": "Replace the chart with a comparison table",
    "slideIndex": 4
  }'

Success response (`200`)

{
  "message": "Edit submitted successfully",
  "resData": {
    "callback_id": "8c1d4b92-6f37-4e2a-a95c-1b0e7d3f6a48"
  },
  "error": null
}

This callback_id is new — not the one you sent. Stream it to watch the edit, and pass it as the callback_id of your next edit to keep building on this version.

`POST /api/v2/autogenerator/download` — Download the file

Returns a stream_url directly — no /streams/sessions step. Open it and read the terminal event for the download_url.

A stream rather than an inline URL because the file may not exist yet:

Case	What you see
Already exported in this format	terminal event immediately, with the `download_url`
Needs exporting	progress events, then the terminal event with the new URL

An export can take several minutes — far longer than an HTTP response allows — which is why both cases are delivered the same way.

Request body

Field	Type	Required	Description
`callback_id`	string	yes	The presentation to download.
`export_type`	string	no	`pptx` or `pdf`. Defaults to your key's configured format, then `pptx`.

Example

curl -X POST https://api.prezent.ai/api/v2/autogenerator/download \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91",
    "export_type": "pptx"
  }'

Success response (`200`)

{
  "message": "Connect to stream_url to receive the download URL on the done event",
  "status": "success",
  "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91",
  "export_type": "pptx",
  "stream_url": "https://stream-api-prod.myprezent.com/v2/streams/a1b2c3?token=eyJhbGciOi...&turn_id=3f8e7d61&stream_type=export&export_type=pptx",
  "expires_at": "2026-08-05T12:34:56.000Z"
}

Fields are at the top level, not under data.

status: "success" confirms the stream was minted — it does not mean the file is ready. Read the stream's terminal event for that.

stream_url expires at expires_at (about 5 minutes). Call the endpoint again for a fresh one.

Quota (`429`)

Download quota is checked before the stream is minted, so a key without room never receives a URL it cannot redeem:

{
  "success": false,
  "data": null,
  "error": {
    "code": "USAGE_LIMIT_EXCEEDED",
    "message": "Usage limit exceeded.",
    "details": "This presentation has 12 slide(s), but only 5 download slide(s) remain on your plan (limit 50000)."
  }
}

`POST /api/v2/streams/sessions` — Get a stream URL

Exchanges a callback_id from generate or edit for an authenticated SSE URL.

Request body

Field	Type	Required	Description
`callback_id`	string	yes	The id from generate or edit.

Example

curl -X POST https://api.prezent.ai/api/v2/streams/sessions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91" }'

Success response (`201`)

{
  "success": true,
  "data": {
    "callback_id": "3f8e7d61-9a2b-4c5e-b013-7d4a6f2c8e91",
    "stream_url": "https://stream-api-prod.myprezent.com/v2/streams/a1b2c3?token=eyJhbGciOi...&turn_id=3f8e7d61",
    "expires_at": "2026-08-05T12:34:56.000Z"
  }
}

The token is in the URL, so send no Authorization header when opening it — browsers' EventSource cannot set headers anyway.

stream_url expires in about 5 minutes. Calling this endpoint again mints a fresh URL, and the stream replays from the start of the turn — so a late reconnect loses nothing.

For an edit, the URL also replays from the point the edit was queued, so you see the whole edit even if you connect a moment late.

Errors

Status	`error.code`	Meaning
`400`	`MISSING_REQUIRED_FIELD`	`callback_id` absent or not a string.
`404`	`STREAM_CALLBACK_NOT_FOUND`	No generation found for this id under your key, or its session expired (~3h).

`GET /api/v1/autogenerator/templates` — List templates

Returns the brand templates available for generation — the values you pass as template_id. Unchanged from 1.0, and still on the v1 path.

Query parameters

Parameter	Type	Required	Description
`name`	string	no	Case-insensitive name filter.
`sort`	string	no	Sort expression (for example `name:asc`).
`source`	string	no	Source filter (`brand` vs `prezent`).
`enabledFeature`	string	no	Optional feature flag filter.
`limit`	integer	no	Items per page (1–200, default 50). Enables pagination.
`cursor`	string	no	Opaque cursor from a previous response's `next_cursor`.

Success response (`200`)

{
  "success": true,
  "data": {
    "items": [
      { "id": "tmpl_corp_2024", "name": "Corporate 2024", "code": "CORP24", "source": "brand" }
    ],
    "next_cursor": null
  }
}

Results are always scoped to the auto_generator feature server-side; the caller cannot override the scoping. See Developer Guide → Pagination.

`GET /api/v2/autogenerator/languages` — List supported languages

The languages a deck can be generated in. Pass a locale from this list as settings.language; an unsupported value is rejected with 422.

The list is static — cache it rather than calling this before every generation.

Example

curl -s https://api.prezent.ai/api/v2/autogenerator/languages \
  -H "Authorization: Bearer YOUR_API_KEY"

Success response (`200`)

{
  "status": "success",
  "message": "Supported languages retrieved successfully",
  "data": [
    { "language": "Arabic", "locale": "ar" },
    { "language": "Chinese (Simplified)", "locale": "zh" },
    { "language": "English (UK)", "locale": "en-uk" },
    { "language": "English (US)", "locale": "en" },
    { "language": "French", "locale": "fr" },
    { "language": "German", "locale": "de" },
    { "language": "Hindi", "locale": "hi" },
    { "language": "Indonesian", "locale": "id" },
    { "language": "Italian", "locale": "it" },
    { "language": "Japanese", "locale": "ja" },
    { "language": "Korean", "locale": "ko" },
    { "language": "Portuguese (Brazil)", "locale": "pt" },
    { "language": "Spanish", "locale": "es" }
  ]
}

`GET /api/v2/integrations/auth` — Connect an app

Connects a third-party app (Google Drive, Notion, …) to the caller's Prezent account. Once connected, a generation can pull context from it by setting settings.enable_mcp_context to true.

The connection is made for the user who owns the API key — there is no parameter to connect an app on someone else's behalf.

Query parameters

Parameter	Type	Required	Description
`mcp_id`	string	yes	Identifier of the app to connect.

Two response shapes

Which you get is a property of the app, not something you choose. Branch on whether status is present.

Authorization required — send the user to the URL:

{ "auth_url": "https://accounts.google.com/o/oauth2/v2/auth?client_id=...&state=..." }

The URL is single-use and time-limited; request a fresh one rather than storing it. After the user authorizes, confirm with /auth/status.

No authorization needed — already done:

{ "status": "connected", "message": "MCP connection successful" }

Errors

Status	`error.code`	Meaning
`400`	`MISSING_REQUIRED_FIELD`	`mcp_id` not supplied.
`404`	`MCP_NOT_FOUND`	No app registered under this `mcp_id`.
`503`	`SERVICE_UNAVAILABLE`	The integrations service is temporarily unreachable.

`GET /api/v2/integrations/auth/status` — Check an app's connection

Whether an app is currently connected for the caller. Use it after sending a user through an authorization URL, and before a generation that depends on the app.

Query parameters

Parameter	Type	Required	Description
`mcp_id`	string	yes	Identifier of the app to check.

Example

curl -s "https://api.prezent.ai/api/v2/integrations/auth/status?mcp_id=google-drive" \
  -H "Authorization: Bearer YOUR_API_KEY"

Success response (`200`)

{ "connected": false }

End-to-end example

Generate a deck, stream it to completion, then download it.

Python
Node.js

import json
import httpx          # pip install httpx httpx-sse
from httpx_sse import connect_sse

BASE = "https://api.prezent.ai"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}


def read_stream(stream_url):
    """Read a v2 stream to its terminal event; return the download_url."""
    # The token is in the URL — send no auth header here.
    with httpx.Client(timeout=None) as sc:
        with connect_sse(sc, "GET", stream_url) as events:
            for sse in events.iter_sse():
                event = json.loads(sse.data)
                print(event["status"], "-", event["message"])
                if event["status"] == "inprogress":
                    continue
                if event["status"] != "success":
                    raise RuntimeError(f"{event['status']}: {event['message']}")
                return event.get("download_url")
    raise RuntimeError("stream closed without a terminal event")


with httpx.Client(base_url=BASE, headers=HEADERS, timeout=30) as c:
    # 1. start the generation
    gen = c.post("/api/v2/generate", json={
        "prompt": "A 10-slide deck on renewable-energy market trends for 2026",
        "template_id": "your-template-id",
    })
    gen.raise_for_status()
    callback_id = gen.json()["resData"]["callback_id"]

    # 2. mint a stream URL, 3. read it to completion
    sess = c.post("/api/v2/streams/sessions", json={"callback_id": callback_id})
    sess.raise_for_status()
    download_url = read_stream(sess.json()["data"]["stream_url"])

    # 4. the generation stream may finish before the file is exported.
    #    A null download_url means "ask for the export", not "failed".
    if not download_url:
        dl = c.post("/api/v2/autogenerator/download", json={
            "callback_id": callback_id,
            "export_type": "pptx",
        })
        dl.raise_for_status()
        download_url = read_stream(dl.json()["stream_url"])

    print("deck ready:", download_url)

import { EventSource } from 'eventsource';   // npm install eventsource

const BASE = 'https://api.prezent.ai';
const HEADERS = {
  Authorization: 'Bearer YOUR_API_KEY',
  'Content-Type': 'application/json',
};

const post = async (path, body) => {
  const res = await fetch(`${BASE}${path}`, {
    method: 'POST',
    headers: HEADERS,
    body: JSON.stringify(body),
  });
  if (!res.ok) throw new Error(`${path} → ${res.status} ${await res.text()}`);
  return res.json();
};

// Read a v2 stream to its terminal event and resolve the download_url.
const readStream = (streamUrl) =>
  new Promise((resolve, reject) => {
    // The token is in the URL — no Authorization header here.
    const es = new EventSource(streamUrl);

    es.onmessage = (e) => {
      const event = JSON.parse(e.data);
      console.log(event.status, '-', event.message);
      if (event.status === 'inprogress') return;

      es.close();
      if (event.status === 'success') resolve(event.download_url ?? null);
      else reject(new Error(`${event.status}: ${event.message}`));
    };

    es.onerror = () => { es.close(); reject(new Error('stream failed')); };
  });

// 1. start
const { resData } = await post('/api/v2/generate', {
  prompt: 'A 10-slide deck on renewable-energy market trends for 2026',
  template_id: 'your-template-id',
});
const callbackId = resData.callback_id;

// 2 + 3. stream to completion
const { data } = await post('/api/v2/streams/sessions', { callback_id: callbackId });
let downloadUrl = await readStream(data.stream_url);

// 4. a null download_url means "ask for the export", not "failed"
if (!downloadUrl) {
  const dl = await post('/api/v2/autogenerator/download', {
    callback_id: callbackId,
    export_type: 'pptx',
  });
  downloadUrl = await readStream(dl.stream_url);
}

console.log('deck ready:', downloadUrl);

Why step 4 exists

On a generation stream, download_url can be null — the deck is built but not yet exported to a file. Treat null as "call download", not as an error. On a download stream it is always populated.

What changed from 1.0

	1.0	2.0
Generate	`POST /api/v1/autogenerator`	`POST /api/v2/generate`
Track progress	poll `GET /api/v1/autogenerator/status`	open an SSE stream
Revise	`regenerate`, `node-change`, `slide-actions`	`POST /api/v2/autogenerator/edit`
Download	`POST /api/v1/autogenerator/download`	`POST /api/v2/autogenerator/download`
Templates	`GET /api/v1/autogenerator/templates`	unchanged

There is no status endpoint in 2.0. Progress arrives as events, so there is no polling loop to write and no interval to tune — and the progress messages are written for display, so you can show them to a user directly.

Editing is one endpoint. Rather than choosing between regenerate, node-change, and slide-actions, describe the change you want. Edits chain, so a sequence of revisions is a conversation.

These 1.0 endpoints have no 2.0 equivalent: status-bulk, meta, slide-data, extract-images, brand-image-search, library-image-search, replace-image, and reaction-feedback. If you depend on any of them, stay on 1.0 — both versions run side by side and there is no forced migration.

Errors

Every error uses the canonical envelope. The codes you are most likely to see on this surface:

Status	`error.code`	Cause
`400`	`BAD_REQUEST`, `INVALID_JSON`, `MISSING_CALLBACK_ID`, `MISSING_REQUIRED_FIELD`, `INVALID_DATA_TYPE`	Malformed request, unknown `callback_id`, deck not ready to edit, `slideIndex` out of range.
`401`	`UNAUTHORIZED`, `INVALID_API_KEY`, `EXPIRED_API_KEY`	Missing, invalid, or expired key.
`404`	`ENDPOINT_NOT_FOUND`, `STREAM_CALLBACK_NOT_FOUND`, `MCP_NOT_FOUND`	Key not scoped to this path, expired session, or unknown app.
`422`	`INVALID_INPUT`	Field validation failed — `error.details` is an array of messages.
`429`	`TOO_MANY_REQUESTS`, `RATE_LIMIT_EXCEEDED`, `USAGE_LIMIT_EXCEEDED`	Gateway throttle, per-category limit, or annual quota.
`500`	`INTERNAL_SERVER_ERROR`	Unexpected server error.
`503`	`SERVICE_UNAVAILABLE`	A downstream service is temporarily unreachable.

Full catalog: Error Reference.

Where to go next

Streaming (SSE) — reconnection, timeouts, and production-ready client patterns.
API Reference — every field, interactively.
Rate Limits — the three limit tiers and how to back off.
Template Converter — apply a brand template to an existing deck (unchanged in 2.0).

Authentication​

Endpoint summary​

How the streaming flow works​

The event contract​

Response envelopes​

POST /api/v2/generate — Generate a presentation​

Request body​

Settings​

Example​

Success response (200)​

Validation errors (422)​

POST /api/v2/autogenerator/edit — Revise a presentation​

Request body​

Example​

Success response (200)​

POST /api/v2/autogenerator/download — Download the file​

Request body​

Example​

Success response (200)​

Quota (429)​

POST /api/v2/streams/sessions — Get a stream URL​

Request body​

Example​

Success response (201)​

Errors​

GET /api/v1/autogenerator/templates — List templates​

Query parameters​

Success response (200)​

GET /api/v2/autogenerator/languages — List supported languages​

Example​

Success response (200)​

GET /api/v2/integrations/auth — Connect an app​

Query parameters​

Two response shapes​

Errors​

GET /api/v2/integrations/auth/status — Check an app's connection​

Query parameters​

Example​

Success response (200)​

End-to-end example​

What changed from 1.0​

Errors​

Where to go next​

Authentication

Endpoint summary

How the streaming flow works

The event contract

Response envelopes

`POST /api/v2/generate` — Generate a presentation

Request body

Settings

Example

Success response (`200`)

Validation errors (`422`)

`POST /api/v2/autogenerator/edit` — Revise a presentation

Request body

Example

Success response (`200`)

`POST /api/v2/autogenerator/download` — Download the file

Request body

Example

Success response (`200`)

Quota (`429`)

`POST /api/v2/streams/sessions` — Get a stream URL

Request body

Example

Success response (`201`)

Errors

`GET /api/v1/autogenerator/templates` — List templates

Query parameters

Success response (`200`)

`GET /api/v2/autogenerator/languages` — List supported languages

Example

Success response (`200`)

`GET /api/v2/integrations/auth` — Connect an app

Query parameters

Two response shapes

Errors

`GET /api/v2/integrations/auth/status` — Check an app's connection

Query parameters

Example

Success response (`200`)

End-to-end example

What changed from 1.0

Errors

Where to go next