Michael Ikehi
369 lines
7.7 KiB
Markdown
369 lines
7.7 KiB
Markdown
# Microdot AI API Documentation
|
|
|
|
## Overview
|
|
|
|
Microdot AI provides a powerful API for transcribing audio/video content and generating AI-powered summaries. The API supports different pricing tiers with varying features and capabilities.
|
|
|
|
## Base URL
|
|
|
|
```
|
|
http://0.0.0.0:5056
|
|
```
|
|
|
|
## Authentication
|
|
|
|
All API requests require authentication using a Bearer token.
|
|
|
|
```
|
|
Authorization: Bearer YOUR_API_KEY
|
|
```
|
|
|
|
## Endpoints
|
|
|
|
### 1. Transcribe Media
|
|
|
|
Transcribes audio or video content from a URL.
|
|
|
|
**Endpoint:** `/microdot-ai/transcribe`
|
|
|
|
**Method:** POST
|
|
|
|
**Request Body:**
|
|
|
|
```json
|
|
{
|
|
"media_url": "https://example.com/audio-file.mp3",
|
|
"media_type": "audio" // "audio" or "video"
|
|
}
|
|
```
|
|
|
|
**Response:**
|
|
|
|
```json
|
|
{
|
|
"transcript": {
|
|
"sentences": [
|
|
{
|
|
"sentence": "Hello and welcome to the meeting.",
|
|
"speaker": "speaker_0",
|
|
"start": 0.0,
|
|
"end": 2.5,
|
|
"words": [
|
|
{
|
|
"word": "Hello",
|
|
"start": 0.0,
|
|
"end": 0.4
|
|
},
|
|
// Additional words...
|
|
]
|
|
},
|
|
// Additional sentences...
|
|
]
|
|
}
|
|
}
|
|
```
|
|
|
|
### 2. Generate General Summary
|
|
|
|
Generates a summary of a transcript based on the user's plan tier.
|
|
|
|
**Endpoint:** `/microdot-ai/general-summary`
|
|
|
|
**Method:** POST
|
|
|
|
**Request Body:**
|
|
|
|
```json
|
|
{
|
|
"transcript": "JSON_STRING_OF_TRANSCRIPT",
|
|
"plan_tier": "pro" // "freemium" or "pro"
|
|
}
|
|
```
|
|
|
|
#### Freemium Plan Response:
|
|
|
|
```json
|
|
{
|
|
"transcript": {
|
|
"Key_Points": [
|
|
{
|
|
"text": "Team discussed Q3 marketing strategy.",
|
|
"timestamp": 120.5
|
|
},
|
|
{
|
|
"text": "Budget approval needed by Friday.",
|
|
"timestamp": 360.2
|
|
},
|
|
{
|
|
"text": "New product launch delayed until September.",
|
|
"timestamp": 480.7
|
|
}
|
|
],
|
|
"Summary": {
|
|
"text": "Marketing team meeting to review Q3 plans and budget requirements. Team agreed on strategy but product launch delayed.",
|
|
"duration_minutes": 15.5
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Pro Plan Response:
|
|
|
|
```json
|
|
{
|
|
"transcript": {
|
|
"Purpose": {
|
|
"text": "Discuss project progress and define upcoming milestones."
|
|
},
|
|
"Chapters": {
|
|
"minutes_total": 3,
|
|
"content": [
|
|
{
|
|
"chapter": "Project Overview",
|
|
"time_stamp": {"start": 5.12, "end": 5.68},
|
|
"content": [
|
|
{"text": "- overview of the project's objectives.", "original_transcript_start": 3.4, "original_transcript_end": 5.7},
|
|
// Additional content...
|
|
],
|
|
"words_time_stamp": [
|
|
{"word": "Project", "timestamp": 5.12},
|
|
{"word": "Overview", "timestamp": 5.12}
|
|
]
|
|
},
|
|
// Additional chapters...
|
|
]
|
|
},
|
|
"Outcomes": {
|
|
"minutes_total": 3,
|
|
"content": [
|
|
// Outcome content...
|
|
]
|
|
},
|
|
"Action_Items_Per_User": [
|
|
{
|
|
"speaker": "Speaker_A",
|
|
"minutes_total": 3,
|
|
"action_items": [
|
|
// Action items...
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|
|
```
|
|
|
|
### 3. Generate Template Summary
|
|
|
|
Generates a custom summary based on a user-defined template.
|
|
|
|
**Endpoint:** `/microdot-ai/template-summary`
|
|
|
|
**Method:** POST
|
|
|
|
**Request Body:**
|
|
|
|
```json
|
|
{
|
|
"transcript": "JSON_STRING_OF_TRANSCRIPT",
|
|
"template": "JSON_STRING_OF_TEMPLATE"
|
|
}
|
|
```
|
|
|
|
**Example Template:**
|
|
|
|
```json
|
|
{
|
|
"Key_Points": "Summarize the most critical discussion points from the meeting.",
|
|
"Summary": "Provide a brief overall summary of what was discussed.",
|
|
"Next_Steps": "List the next steps decided during the meeting, including any action items."
|
|
}
|
|
```
|
|
|
|
**Response:**
|
|
|
|
```json
|
|
{
|
|
"transcript": {
|
|
"Key_Points": {
|
|
"minutes_total": 3.5,
|
|
"content": [
|
|
{
|
|
"text": "Introductions between Diane Taylor and Cody Smith.",
|
|
"time_stamp": {"start": 5.12, "end": 5.68},
|
|
"words_time_stamp": [
|
|
{"word": "Introductions", "timestamp": 5.12},
|
|
// Additional words...
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"Summary": {
|
|
// Summary content...
|
|
},
|
|
"Next_Steps": {
|
|
// Next steps content...
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
## Plan Features
|
|
|
|
### Freemium Plan
|
|
|
|
- 200 minutes of transcription per month
|
|
- Basic AI summarization (short bullet points)
|
|
- 7-day transcript history
|
|
- Limited integrations (Google Meet & Zoom only)
|
|
|
|
### Pro Plan
|
|
|
|
- 600 minutes of transcription per month
|
|
- Advanced AI summarization with action items
|
|
- Speaker identification
|
|
- 30-day transcript history
|
|
- Multi-platform integrations (Slack, Notion, Asana, Microsoft Teams)
|
|
|
|
## Error Responses
|
|
|
|
All endpoints return standard HTTP status codes:
|
|
|
|
- `200 OK`: Request successful
|
|
- `400 Bad Request`: Invalid request parameters
|
|
- `401 Unauthorized`: Invalid or missing API key
|
|
- `500 Internal Server Error`: Server-side error
|
|
|
|
Error response format:
|
|
|
|
```json
|
|
{
|
|
"detail": {
|
|
"error": "Error type",
|
|
"message": "Detailed error message"
|
|
}
|
|
}
|
|
```
|
|
|
|
## Rate Limits
|
|
|
|
- Freemium Plan: 100 requests per day
|
|
- Pro Plan: 1000 requests per day
|
|
|
|
Exceeding your plan's transcription minutes will result in a `402 Payment Required` response until the next billing cycle.
|
|
|
|
## Code Examples
|
|
|
|
### Python
|
|
|
|
```python
|
|
import requests
|
|
import json
|
|
|
|
# API endpoint
|
|
base_url = "https://api.microdot.ai"
|
|
|
|
# Your API key
|
|
api_key = "your_api_key_here"
|
|
|
|
# Headers
|
|
headers = {
|
|
"Authorization": f"Bearer {api_key}",
|
|
"Content-Type": "application/json"
|
|
}
|
|
|
|
# 1. Transcribe an audio file
|
|
transcribe_payload = {
|
|
"media_url": "https://example.com/meeting-recording.mp3",
|
|
"media_type": "audio"
|
|
}
|
|
|
|
transcribe_response = requests.post(
|
|
f"{base_url}/microdot-ai/transcribe",
|
|
headers=headers,
|
|
json=transcribe_payload
|
|
)
|
|
|
|
# Check if transcription was successful
|
|
if transcribe_response.status_code == 200:
|
|
transcript_data = transcribe_response.json()
|
|
transcript_json = json.dumps(transcript_data["transcript"])
|
|
|
|
# 2. Generate a summary (Pro plan)
|
|
summary_payload = {
|
|
"transcript": transcript_json,
|
|
"plan_tier": "pro"
|
|
}
|
|
|
|
summary_response = requests.post(
|
|
f"{base_url}/microdot-ai/general-summary",
|
|
headers=headers,
|
|
json=summary_payload
|
|
)
|
|
|
|
if summary_response.status_code == 200:
|
|
summary_data = summary_response.json()
|
|
print("Summary generated successfully!")
|
|
print(json.dumps(summary_data["transcript"], indent=2))
|
|
else:
|
|
print(f"Summary generation failed: {summary_response.text}")
|
|
else:
|
|
print(f"Transcription failed: {transcribe_response.text}")
|
|
```
|
|
|
|
### JavaScript
|
|
|
|
```javascript
|
|
const axios = require('axios');
|
|
|
|
// API endpoint
|
|
const baseUrl = 'https://api.microdot.ai';
|
|
|
|
// Your API key
|
|
const apiKey = 'your_api_key_here';
|
|
|
|
// Headers
|
|
const headers = {
|
|
'Authorization': `Bearer ${apiKey}`,
|
|
'Content-Type': 'application/json'
|
|
};
|
|
|
|
// 1. Transcribe an audio file
|
|
const transcribeAudio = async () => {
|
|
const transcribePayload = {
|
|
media_url: 'https://example.com/meeting-recording.mp3',
|
|
media_type: 'audio'
|
|
};
|
|
|
|
try {
|
|
const transcribeResponse = await axios.post(
|
|
`${baseUrl}/microdot-ai/transcribe`,
|
|
transcribePayload,
|
|
{ headers }
|
|
);
|
|
|
|
const transcriptData = transcribeResponse.data;
|
|
const transcriptJson = JSON.stringify(transcriptData.transcript);
|
|
|
|
// 2. Generate a summary (Pro plan)
|
|
const summaryPayload = {
|
|
transcript: transcriptJson,
|
|
plan_tier: 'pro'
|
|
};
|
|
|
|
const summaryResponse = await axios.post(
|
|
`${baseUrl}/microdot-ai/general-summary`,
|
|
summaryPayload,
|
|
{ headers }
|
|
);
|
|
|
|
console.log('Summary generated successfully!');
|
|
console.log(JSON.stringify(summaryResponse.data.transcript, null, 2));
|
|
|
|
} catch (error) {
|
|
console.error('Error:', error.response ? error.response.data : error.message);
|
|
}
|
|
};
|
|
|
|
transcribeAudio();
|
|
```
|