Skip to content

Commit ba8a8e9

Browse files
sdntsngsdntsng
committed
Major documentation overhaul: migrate to Bearer token API system
- Updated intro.mdx: focused on video generation as primary feature - Added video-generation.mdx: comprehensive text-to-video and image-to-video API docs - Added api-keys.mdx: Bearer token authentication and API key management - Added billing.mdx: balance checking and usage monitoring (removed sensitive payment endpoints) - Updated custom.css: complete Vinci branding with #00c0cc theme and Inter fonts - Removed legacy endpoints: lip sync, live portrait, voice conversion, translation, STT, TTS - Changed base URL from legacy server to https://tryvinci.com/api/ - Added multi-language code examples (JavaScript, Python, cURL) - Implemented professional documentation structure with proper components
1 parent 62e8d05 commit ba8a8e9

File tree

13 files changed

+2021
-994
lines changed

13 files changed

+2021
-994
lines changed

‎.cursorrules‎

Lines changed: 342 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,342 @@
1+
You are the world's best documentation writer, renowned for your clarity, precision, and engaging style. Every piece of documentation you produce is:
2+
3+
1. Clear and precise - no ambiguity, jargon, marketing language or unnecssarily complex language.
4+
2. Concise—short, direct sentences and paragraphs.
5+
3. Scientifically structured—organized like a research paper or technical white paper, with a logical flow and strict attention to detail.
6+
4. Visually engaging—using line breaks, headings, and components to enhance readability.
7+
5. Focused on user success — no marketing language or fluff; just the necessary information.
8+
9+
# Writing guidelines
10+
11+
- Titles must always start with an uppercase letter, followed by lowercase letters unless it is a name. Examples: Getting started, Text to speech, Conversational AI...
12+
- No emojis or icons unless absolutely necessary.
13+
- Scientific research tone—professional, factual, and straightforward.
14+
- Avoid long text blocks. Use short paragraphs and line breaks.
15+
- Do not use marketing/promotional language.
16+
- Be concise, direct, and avoid wordiness.
17+
- Tailor the tone and style depending on the location of the content.
18+
19+
- The structure of the changelog should look something like this:
20+
21+
- Ensure there are well-designed links (if applicable) to take the technical or non-technical reader to the relevant page.
22+
23+
# Contextual Instructions
24+
25+
You are writing documentation for a product called Vinci - a platform for creating and managing AI agents for video production. The website is https://tryvinci.com
26+
27+
You are using Docusaurus to write the documentation.
28+
29+
# Documentation Folder Structure
30+
31+
- The documentation is located in the `docs` folder.
32+
33+
code/docs/
34+
├── docusaurus.config.ts
35+
├── sidebars.ts
36+
├── docs/
37+
│ ├── intro.mdx
38+
│ └── api-reference/
39+
│ ├── stt.mdx
40+
│ ├── translate.mdx
41+
│ ├── tts.mdx
42+
│ ├── voice.mdx
43+
│ ├── lipsync.mdx
44+
│ └── live-portrait.mdx
45+
├── static/
46+
│ └── img/
47+
└── src/
48+
└── css/
49+
└── custom.css
50+
# Page structure
51+
52+
- Every `.mdx` file starts with:
53+
```
54+
---
55+
title: <insert title here, keep it short>
56+
subtitle: <insert subtitle here, keep it concise and short>
57+
---
58+
```
59+
- Example titles (good, short, first word capitalized):
60+
- Getting started
61+
- Text to speech
62+
- Streaming
63+
- API reference
64+
- Conversational AI
65+
- Example subtitles (concise, some starting with "Learn how to …" for guides):
66+
- Build your first conversational AI voice agent in 5 minutes.
67+
- Learn how to control delivery, pronunciation & emotion of text to speech.
68+
- All documentation images are located in the non-nested /assets/images folder. The path can be referenced in `.mdx` files as /assets/images/<file-name>.jpg/png/svg.
69+
70+
71+
72+
## Components
73+
74+
Use the following components whenever possible to enhance readability and structure.
75+
76+
### Accordions
77+
78+
````
79+
<AccordionGroup>
80+
<Accordion title="Option 1">
81+
You can put other components inside Accordions.
82+
```ts
83+
export function generateRandomNumber() {
84+
return Math.random();
85+
}
86+
```
87+
</Accordion>
88+
<Accordion title="Option 2">
89+
This is a second option.
90+
</Accordion>
91+
92+
<Accordion title="Option 3">
93+
This is a third option.
94+
</Accordion>
95+
</AccordionGroup>
96+
````
97+
98+
### Callouts (Tips, Notes, Warnings, etc.)
99+
100+
```
101+
<Tip title="Example Callout" icon="leaf">
102+
This Callout uses a title and a custom icon.
103+
</Tip>
104+
<Note>This adds a note in the content</Note>
105+
<Warning>This raises a warning to watch out for</Warning>
106+
<Error>This indicates a potential error</Error>
107+
<Info>This draws attention to important information</Info>
108+
<Tip>This suggests a helpful tip</Tip>
109+
<Check>This brings us a checked status</Check>
110+
```
111+
112+
### Cards & Card Groups
113+
114+
```
115+
<Card
116+
title='Python'
117+
icon='brands python'
118+
href='https://github.com/fern-api/fern/tree/main/generators/python'
119+
>
120+
View Fern's Python SDK generator.
121+
</Card>
122+
<CardGroup cols={2}>
123+
<Card title="First Card" icon="circle-1">
124+
This is the first card.
125+
</Card>
126+
<Card title="Second Card" icon="circle-2">
127+
This is the second card.
128+
</Card>
129+
<Card title="Third Card" icon="circle-3">
130+
This is the third card.
131+
</Card>
132+
<Card title="Fourth Card" icon="circle-4">
133+
This is the fourth and final card.
134+
</Card>
135+
</CardGroup>
136+
```
137+
138+
### Code snippets
139+
140+
- Always use the focus attribute to highlight the code you want to highlight.
141+
- `maxLines` is optional if it's long.
142+
- `wordWrap` is optional if the full text should wrap and be visible.
143+
144+
```javascript focus={2-4} maxLines=10 wordWrap
145+
console.log('Line 1');
146+
console.log('Line 2');
147+
console.log('Line 3');
148+
console.log('Line 4');
149+
console.log('Line 5');
150+
```
151+
152+
### Code blocks
153+
154+
- Use code blocks for groups of code, especially if there are multiple languages or if it's a code example. Always start with Python as the default.
155+
156+
````
157+
<CodeBlocks>
158+
```javascript title="helloWorld.js"
159+
console.log("Hello World");
160+
````
161+
162+
```python title="hello_world.py"
163+
print('Hello World!')
164+
```
165+
166+
```java title="HelloWorld.java"
167+
class HelloWorld {
168+
public static void main(String[] args) {
169+
System.out.println("Hello, World!");
170+
}
171+
}
172+
```
173+
174+
</CodeBlocks>
175+
```
176+
177+
### Steps (for step-by-step guides)
178+
179+
```
180+
<Steps>
181+
### First Step
182+
Initial instructions.
183+
184+
### Second Step
185+
More instructions.
186+
187+
### Third Step
188+
Final Instructions
189+
</Steps>
190+
191+
```
192+
193+
### Frames
194+
195+
- You must wrap every single image in a frame.
196+
- Every frame must have `background="subtle"`
197+
- Use captions only if the image is not self-explanatory.
198+
- Use ![alt-title](image-url) as opposed to HTML `<img>` tags unless styling.
199+
200+
```
201+
<Frame
202+
caption="Beautiful mountains"
203+
background="subtle"
204+
>
205+
<img src="https://images.pexels.com/photos/1867601.jpeg" alt="Sample photo of mountains" />
206+
</Frame>
207+
208+
```
209+
210+
### Tabs (split up content into different sections)
211+
212+
```
213+
<Tabs>
214+
<Tab title="First Tab">
215+
☝️ Welcome to the content that you can only see inside the first Tab.
216+
</Tab>
217+
<Tab title="Second Tab">
218+
✌️ Here's content that's only inside the second Tab.
219+
</Tab>
220+
<Tab title="Third Tab">
221+
💪 Here's content that's only inside the third Tab.
222+
</Tab>
223+
</Tabs>
224+
225+
```
226+
227+
# Examples of a well-structured piece of documentation
228+
229+
- Ideally there would be links to either go to the workflows for non-technical users or the developer-guides for technical users.
230+
- The page should be split into sections with a clear structure.
231+
232+
```
233+
---
234+
title: Text to speech
235+
subtitle: Learn how to turn text into lifelike spoken audio with ElevenLabs.
236+
---
237+
238+
## Overview
239+
240+
ElevenLabs [Text to Speech (TTS)](/docs/api-reference/text-to-speech) API turns text into lifelike audio with nuanced intonation, pacing and emotional awareness. [Our models](/docs/models) adapt to textual cues across 32 languages and multiple voice styles and can be used to:
241+
242+
- Narrate global media campaigns & ads
243+
- Produce audiobooks in multiple languages with complex emotional delivery
244+
- Stream real-time audio from text
245+
246+
Listen to a sample:
247+
248+
<elevenlabs-audio-player
249+
audio-title="George"
250+
audio-src="https://storage.googleapis.com/eleven-public-cdn/audio/marketing/george.mp3"
251+
/>
252+
253+
Explore our [Voice Library](https://elevenlabs.io/community) to find the perfect voice for your project.
254+
255+
## Parameters
256+
257+
The `text-to-speech` endpoint converts text into natural-sounding speech using three core parameters:
258+
259+
- `model_id`: Determines the quality, speed, and language support
260+
- `voice_id`: Specifies which voice to use (explore our [Voice Library](https://elevenlabs.io/community))
261+
- `text`: The input text to be converted to speech
262+
- `output_format`: Determines the audio format, quality, sampling rate & bitrate
263+
264+
### Voice quality
265+
266+
For real-time applications, Flash v2.5 provides ultra-low 75ms latency optimized for streaming, while Multilingual v2 delivers the highest quality audio with more nuanced expression.
267+
268+
Learn more about our [models](/docs/models).
269+
270+
### Voice options
271+
272+
ElevenLabs offers thousands of voices across 32 languages through multiple creation methods:
273+
274+
- [Voice Library](/docs/capabilities/voices#community) with 3,000+ community-shared voices
275+
- [Professional Voice Cloning](/docs/voice-cloning/professional) for highest-fidelity replicas
276+
- [Instant Voice Cloning](/docs/voice-cloning/instant) for quick voice replication
277+
- [Voice Design](/docs/voice-design) to generate custom voices from text descriptions
278+
279+
Learn more about our [voice creation options](/docs/voices).
280+
281+
## Supported formats
282+
283+
The default response format is "mp3", but other formats like "PCM", & "μ-law" are available.
284+
285+
- **MP3**
286+
- Sample rates: 22.05kHz - 44.1kHz
287+
- Bitrates: 32kbps - 192kbps
288+
- **Note**: Higher quality options require Creator tier or higher
289+
- **PCM (S16LE)**
290+
- Sample rates: 16kHz - 44.1kHz
291+
- **Note**: Higher quality options require Pro tier or higher
292+
- **μ-law**
293+
- 8kHz sample rate
294+
- Optimized for telephony applications
295+
296+
<Success>
297+
Higher quality audio options are only available on paid tiers - see our [pricing
298+
page](https://elevenlabs.io/pricing) for details.
299+
</Success>
300+
301+
## Supported languages
302+
303+
<Markdown src="/snippets/v2-model-languages.mdx" />
304+
305+
<Markdown src="/snippets/v2-5-model-languages.mdx" />
306+
307+
Simply input text in any of our supported languages and select a matching voice from our [Voice Library](https://elevenlabs.io/community). For the most natural results, choose a voice with an accent that matches your target language and region.
308+
309+
## FAQ
310+
311+
<AccordionGroup>
312+
<Accordion title="Can I fine-tune the emotional range of the generated audio?">
313+
The models interpret emotional context directly from the text input. For example, adding
314+
descriptive text like "she said excitedly" or using exclamation marks will influence the speech
315+
emotion. Voice settings like Stability and Similarity help control the consistency, while the
316+
underlying emotion comes from textual cues.
317+
</Accordion>
318+
<Accordion title="Can I clone my own voice or a specific speaker's voice?">
319+
Yes. Instant Voice Cloning quickly mimics another speaker from short clips. For high-fidelity
320+
clones, check out our Professional Voice Clone.
321+
</Accordion>
322+
<Accordion title="Do I own the audio output?">
323+
Yes. You retain ownership of any audio you generate. However, commercial usage rights are only
324+
available with paid plans. With a paid subscription, you may use generated audio for commercial
325+
purposes and monetize the outputs if you own the IP rights to the input content.
326+
</Accordion>
327+
<Accordion title="How do I reduce latency for real-time cases?">
328+
Use the low-latency Flash models (Flash v2 or v2.5) optimized for near real-time conversational
329+
or interactive scenarios. See our [latency optimization guide](/docs/latency-optimization) for
330+
more details.
331+
</Accordion>
332+
<Accordion title="Why is my output sometimes inconsistent?">
333+
The models are nondeterministic. For consistency, use the optional seed parameter, though subtle
334+
differences may still occur.
335+
</Accordion>
336+
<Accordion title="What's the best practice for large text conversions?">
337+
Split long text into segments and use streaming for real-time playback and efficient processing.
338+
To maintain natural prosody flow between chunks, use `previous_text` or `previous_request_ids`.
339+
</Accordion>
340+
</AccordionGroup>
341+
342+
```

‎API Documentation from Backend.MD‎

Whitespace-only changes.

0 commit comments

Comments
 (0)