canonical: https://jentic.com/apis/bisque.cloud/bisque

# Bisque API

The Bisque API turns an HTML file an agent wrote into a narrated presentation on a shareable watch link, and lets an agent read any shared presentation back as a plain-text transcript. It publishes a presentation in one request or builds one incrementally by adding and narrating slides, reports narration and publish progress, and returns an oEmbed card for a watch URL. A public authoring-format spec tells an agent how to write valid presentation HTML before it publishes.

## For AI agents

Turn HTML an agent wrote into a narrated, shareable presentation and read any shared presentation back as a transcript. Publish from HTML, build slide by slide, narrate, track progress, and embed via oEmbed across 41 endpoints.

## Scope

Does not host live video calls, record meetings, or design slides visually. Use for publishing and reading narrated HTML presentations only.

## Capabilities

- Publish a presentation from an HTML file to a shareable watch link
- Narrate a presentation's slides and track publish progress
- Read any shared presentation back as a plain-text transcript
- Build a presentation incrementally by adding and narrating slides, then finalize it
- Get an oEmbed card for a presentation's watch URL
- Fetch the authoring-format spec so an agent writes valid presentation HTML

## Use cases

### Publish an agent-written deck through Jentic

Let an agent turn the HTML it just wrote into a narrated presentation on a shareable link. The agent submits the HTML, Bisque narrates and publishes it, and the status operation reports progress until the watch link is ready. Through Jentic the create operation is discovered by intent and called with its input schema, so publishing fits into the agent's flow.

Example prompt: Publish a presentation from HTML with POST `/api/presentations/create`, then poll GET `/api/presentations/status` until it is ready

### Read a presentation as a transcript

Give an agent the full text of a presentation it was linked to so it can summarize, quote, or answer questions about it. The context operation returns a presentation as plain text with no credentials needed, and a batch form reads several at once.

Example prompt: Read a shared presentation as text with GET `/api/presentations/context`

### Build a presentation slide by slide

Create a presentation and fill it in over several steps instead of publishing in one shot. The agent opens a live creation, adds slides as it drafts them, narrates each one, and finalizes when the deck is complete, so a long presentation can be assembled progressively.

Example prompt: Create a live presentation with POST `/v1/presentations`, add slides with PATCH `/v1/presentations/{presentationId}`, then narrate one with PATCH `/v1/presentations/{presentationId}/slides/{slideKey}`

### Embed a presentation

Surface a published presentation inside another page or chat with a proper preview card. The agent requests the oEmbed card for a watch URL and drops the returned embed markup wherever the deck should appear.

Example prompt: Get an embed card with GET `/api/oembed` for a presentation's watch URL

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/presentations/create` | Publish a presentation from HTML |
| GET | `/api/presentations` | List your presentations |
| GET | `/api/presentations/context` | Read a presentation as text |
| GET | `/api/presentations/status` | Narration and publish progress |
| POST | `/v1/presentations` | Create a presentation and put its slides up |
| PATCH | `/v1/presentations/{presentationId}` | Add slides to a live creation |
| GET | `/api/presentations/spec` | Get the authoring format |
| GET | `/api/oembed` | oEmbed for a watch URL |

## Key resources

- **Read** — Read presentation transcripts, fetch the authoring format, and get oEmbed cards
- **Publish** — Publish presentations from HTML, list them, and track narration progress
- **Live creation** — Create a presentation, add and narrate slides, and finalize it

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 66 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 77 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 48 / 100
  - Agent Usability: 94 / 100
  - Security: 75 / 100
  - AI Discoverability: 74 / 100
- **View full report:** https://jentic.com/apis/bisque.cloud/bisque/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring Bisque by hand means learning its bearer and OAuth2 auth, the HTML authoring format, and the two creation flows for one-shot and incremental publishing. Through Jentic you install once, import Bisque from the API Directory, store the credential once, and your agent calls it.
- **Permission scoping:** Bisque puts the presentation id in the URL path (`/v1/presentations/{presentationId}/...`), so a rule can pin your agent to building and narrating one presentation. You choose which operations it may call, so publishing new presentations or reading others stays out unless you add them.
- **Credential handling:** Your Bisque credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'publish a presentation from HTML' or 'read a presentation as text', and Jentic returns the matching Bisque operation with its input schema so the agent calls the right endpoint without reading the reference docs.

## Related APIs

- **SlideSpeak API** — SlideSpeak generates and summarizes slide decks; Bisque publishes narrated presentations from HTML and reads them back as text.
- **MagicSlides API** — MagicSlides builds presentation slides from text or a topic; Bisque narrates and hosts a presentation on a watch link.
- **Google Slides API** — Google Slides edits slide decks in Workspace; Bisque turns HTML into a narrated, hosted presentation.

## FAQ

### What authentication does the Bisque API use?

The Bisque API authenticates with a bearer token, and it also supports an OAuth2 authorization-code flow, per its OpenAPI spec. Publishing a presentation needs a credential, while reading the authoring format, reading a shared presentation, and oEmbed are public. Through Jentic the credential is stored encrypted by your own Jentic One instance and injected at call time.

### Can I read a shared presentation as text with the Bisque API?

Yes. The context operation returns a presentation as plain text with no credentials needed, and a batch form reads up to 20 presentations in one request, so an agent can summarize or quote a deck it was linked to.

### Can I limit what my agent is allowed to do with the Bisque API?

Yes. Write a rule that allows only the read operations, so your agent can fetch presentation transcripts and the authoring format but cannot publish or finalize presentations unless you add those operations. Bisque carries the presentation id in the URL path, so building a single presentation can be bounded to that one resource.

### What are the rate limits for the Bisque API?

The OpenAPI spec does not specify rate limits. Check the Bisque documentation at https://bisque.cloud for current limits before publishing presentations in bulk.

### Is there a Bisque MCP server?

Yes, Bisque offers its own MCP server. You can also connect it directly through Jentic: your agent gets the full 41-endpoint surface without loading another server's tool definitions into its context, your credential is injected at call time by your self-hosted instance instead of living in a config file, and your rules decide which operations the agent may call.

### How do I publish a presentation from HTML with the Bisque API through Jentic?

Search Jentic for 'publish a presentation from HTML' and it returns the Bisque create operation with its input schema. Your agent sends the HTML, Bisque narrates and publishes it to a watch link, and the status operation reports progress. To run it on your own infrastructure, install Jentic One from its GitHub repo.