Suprsonic is a unified API for AI agents. Instead of integrating dozens of providers for search, scraping, enrichment, image generation, transcription, messaging, and more, you add one API key and get all of them.
No provider authentication required. Suprsonic manages all provider subscriptions internally. You never need OAuth flows, per-provider API keys, or token management for any capability. Just your Suprsonic key.
Every capability uses the same authentication, the same response format, and the same credit system. If a provider fails, Suprsonic automatically falls back to the next one. You don't manage retries, credentials, or individual provider accounts.
Available as a REST API, Python SDK, TypeScript SDK, and MCP server. Use whichever fits your stack.
Step 1: Get your API key
Create a key in the API Keys tab. It starts with omk_ and works across every capability.
Step 2: Make your first call
pip install suprsonic
from suprsonic import Suprsonic
client = Suprsonic("omk_your_key")
result = client.search("latest AI funding rounds")
print(result.data)npm install suprsonic
import { Suprsonic } from "suprsonic";
const client = new Suprsonic("omk_your_key");
const result = await client.search("latest AI funding rounds");
console.log(result.data);{
"suprsonic": {
"command": "npx",
"args": ["-y", "suprsonic-mcp"],
"env": { "SUPRSONIC_API_KEY": "omk_your_key" }
}
}curl -X POST https://suprsonic.ai/v1/search \
-H "Authorization: Bearer omk_your_key" \
-H "Content-Type: application/json" \
-d '{"query": "latest AI funding rounds", "mode": "ai"}'All four methods hit the same API, use the same key, and deduct from the same credit balance.
All unified agent APIs use Bearer token authentication. Include your API key in the Authorization header of every request.
Authorization: Bearer omk_your_key_hereAPI keys are created in the API Keys section. Each key works across all capabilities and is tied to your account and credit balance. Keys can be revoked at any time.
Rate limits
Default: 60 requests per minute per key. Rate limit headers are included in every response:
X-RateLimit-Remaining: 58
X-RateLimit-Limit: 60
X-RateLimit-Reset: 1713400060
X-Credits-Used: 2Each capability costs a fixed number of credits per successful call. Failed requests are free. Capabilities with modes let you choose the cost/quality tradeoff.
/v1/search
SERP: 1AI: 2Deep: 3Search the web with SERP, AI synthesis, or both
/v1/scrape
Fast: 1Standard: 2Thorough: 5Extract content from any URL as Markdown or HTML
/v1/profiles/find
3 creditsFind and enrich professional profiles
/v1/emails/find
2 creditsFind professional email addresses
/v1/images/generate
3 creditsGenerate images from text prompts
/v1/speech/synthesize
2 creditsConvert text to speech audio
/v1/speech/transcribe
2 creditsTranscribe audio to text with timestamps
/v1/sounds/generate
4 creditsGenerate sound effects and short music tracks from text prompts (NOT speech: use tts for spoken voice)
/v1/messages/send
1 creditSend SMS or WhatsApp messages. Default channel is SMS (reliable delivery). WhatsApp requires recipient opt-in: they must have messaged your Business number within 24 hours.
/v1/documents/extract
3 creditsExtract structured data from URLs or content
/v1/companies/find
3 creditsEnrich company data by domain
/v1/emails/verify
1 creditCheck if an email is deliverable, catch-all, or disposable
/v1/audio/transcribe
3 creditsTranscribe audio with speaker diarization and timestamps
/v1/invoices/parse
3 creditsExtract structured data from invoices and receipts
/v1/subtitles/generate
2 creditsGenerate SRT/VTT subtitles from audio or video
/v1/files/convert
2 creditsConvert files between 200+ formats
/v1/images/remove-background
2 creditsRemove background from any image. Returns transparent PNG.
/v1/screenshots/capture
1 creditCapture a rendered screenshot of any webpage
/v1/code/execute
2 creditsExecute code in a secure sandbox with pre-configured environments
/v1/sites/intel
Overview: 2WHOIS: 1DNS: 1Tech Stack: 2Security: 2Subdomains: 2Get comprehensive domain intelligence: WHOIS, DNS, SSL, tech stack, email security, hosting
/v1/research
Standard: 10Deep: 20Comprehensive: 35Multi-step deep research: search, scrape, enrich entities, and synthesize into a cited report
/v1/video/info
1 creditExtract video metadata, available formats, and thumbnail from any URL
/v1/video/download
Video: 3Audio: 2Download video from any URL and return a temporary download link
The Agent API (/v1/agent) costs the same as whichever capability it routes to. Credits are returned in the credits_used field and the X-Credits-Used response header.
All errors follow RFC 7807 (Problem Details for HTTP APIs) with additional fields for agent consumption.
{
"success": false,
"error": {
"type": "https://api.o-mega.ai/errors/rate-limited",
"title": "Rate limit exceeded",
"status": 429,
"detail": "You have exceeded 60 requests per minute",
"is_retriable": true,
"retry_after_seconds": 42,
"alternative_action": "Reduce request frequency or contact support",
"error_category": "transient"
},
"credits_used": 0
}Error categories
Temporary issue. Safe to retry after retry_after_seconds.
Request is invalid. Do not retry with the same parameters.
API key is missing, invalid, or revoked.
Insufficient credits. Upgrade plan or enable overage.
The target content could not be accessed (blocked, CAPTCHA, etc).
HTTP status codes
Success. The request completed and data is in the response.
Bad request. Missing or invalid parameters.
Unauthorized. API key is missing or invalid.
Insufficient credits. Upgrade or enable overage.
Unprocessable. The request was valid but the operation failed (e.g. scrape blocked).
Rate limited. Retry after the specified interval.
Provider error. All upstream providers failed.
Every response uses the same format, regardless of which capability or provider handled the request. This makes it easy for agents to parse responses uniformly.
{
"success": boolean,
"data": { ... } | null,
"error": { ... } | null,
"metadata": {
"provider_used": "string | null",
"providers_tried": ["string"],
"mode_used": "string | null",
"response_time_ms": number,
"request_id": "string"
},
"credits_used": number
}Metadata fields
provider_used
string
Which provider's data was used in the final response. 'merged' if data came from multiple providers.
providers_tried
string[]
All providers that were attempted in the waterfall, in order.
mode_used
string
The mode that was applied (e.g. 'ai', 'standard').
response_time_ms
number
Total wall-clock time for the request in milliseconds.
request_id
string
Unique request identifier for debugging and support.
Every package uses the same API key and hits the same backend. Pick whichever fits your stack.
MCP Server
$ npx suprsonic-mcpWorks with Claude Desktop, Cursor, VS Code, ChatGPT. Your agent gets every capability as MCP tools.
Python SDK
$ pip install suprsonicFor LangChain, CrewAI, OpenAI Agents SDK, Claude API, or any Python agent.
TypeScript SDK
$ npm install suprsonicFor Vercel AI SDK, LangChain.js, Node.js agents, or any TypeScript project.
REST API
Works with any language or framework. Use curl or any HTTP client with a Bearer token.
Machine-readable formats
For auto-generating clients or configuring agent frameworks:
OpenAPI spec
/v1/openapi.jsonFiltered OpenAPI 3.1 spec with only Suprsonic capabilities.
Tool definitions
/v1/tools?format=openaiPre-built tool schemas for OpenAI, Claude, and MCP. Formats: openai, claude, mcp, raw.
llms.txt
/llms.txtAI-readable documentation index for agent discovery.
Suprsonic provides machine-readable tool definitions that any AI agent framework can consume directly. One tool definition gives your agent access to all capabilities. No manual configuration needed.
Tool definition endpoint
Fetch a ready-to-use tool definition, auto-generated from the API schema. No auth required. Choose the format that matches your agent framework.
OpenAI-compatible function calling schema
Anthropic-compatible tool use schema
Model Context Protocol schema (for MCP clients)
Full JSON with per-capability parameter schemas, types, defaults, and descriptions
How it works
Your agent or AI coder fetches the tool definition once, registers it, and routes tool calls to POST /v1/agent. The tool definition contains all parameter names, types, required/optional markers, defaults, and descriptions. No hardcoding needed.
# 1. Fetch the tool definition (pick your format)
GET https://suprsonic.ai/v1/tools?format=openai
# 2. Register it as a tool in your agent framework
# The response is a complete tool schema. Pass it directly.
# 3. When the agent calls the tool, forward to /v1/agent
POST https://suprsonic.ai/v1/agent
Authorization: Bearer omk_your_key_here
Content-Type: application/json
{"capability": "search", "params": {"query": "..."}}The tool definition updates automatically when capabilities are added or parameters change. Fetch it at startup or cache it.
Other discovery endpoints
OpenAPI spec
/v1/openapi.jsonFiltered OpenAPI 3.1 spec for auto-generating typed clients in any language.
llms.txt
/llms.txtAI-readable documentation index for coding agents and RAG pipelines.
One endpoint for every capability.
Instead of registering dozens of separate tools, your agent registers one: POST /v1/agent. Specify the capability and parameters, and the system routes internally. Same response format regardless of which capability you call.
POST /v1/agent
{
"capability": "emails",
"params": {
"first_name": "Yuma",
"last_name": "Heymans",
"domain": "o-mega.ai"
}
}Available capabilities
/v1/search
Search the web and get AI-synthesized answers, raw Google SERP results, or both combined, with automatic provider routing.
/v1/scrape
Extract content from any URL with automatic escalation from fast HTTP fetch to JS rendering to stealth browser with CAPTCHA solving.
/v1/profiles/find
Find and enrich professional profiles by LinkedIn URL or name, with waterfall across multiple data providers and merged results.
/v1/emails/find
Find verified professional email addresses by name and company domain.
/v1/images/generate
Generate images from text prompts using Google GenAI with automatic fallback to DALL-E.
/v1/speech/synthesize
Convert text to natural speech using Deepgram Aura with ElevenLabs fallback.
/v1/speech/transcribe
Transcribe audio via Deepgram with confidence scores and word-level timing.
/v1/sounds/generate
Generate sound effects, ambient audio, foley, and short instrumental music tracks from text descriptions. This is NOT text-to-speech: it does not produce spoken words. For voice/narration, use the tts capability instead.
/v1/messages/send
Send SMS messages reliably. WhatsApp available with recipient opt-in.
/v1/documents/extract
Extract structured data using LLM-powered analysis with a user-defined schema.
/v1/companies/find
Enrich company data with firmographics from Apollo, brand identity from BrandFetch, and qualitative analysis via LLM.
/v1/emails/verify
Check if an email is deliverable, catch-all, or disposable.
/v1/audio/transcribe
Transcribe audio/video with speaker diarization and timestamps.
/v1/invoices/parse
Extract line items, totals, dates from invoices and receipts.
/v1/subtitles/generate
Generate SRT/VTT subtitles from audio or video files.
/v1/files/convert
Convert files between 200+ formats (PDF, DOCX, XLSX, images).
/v1/images/remove-background
Remove background from any image using AI segmentation.
/v1/screenshots/capture
Capture a rendered screenshot of any webpage.
/v1/code/execute
Execute Python, JavaScript, or shell code in an isolated Firecracker microVM sandbox.
/v1/sites/intel
Get WHOIS, DNS records, SSL analysis, technology fingerprinting, email security, and hosting data for any domain in one call.
/v1/research
Deep research that searches the web, scrapes full content, enriches people and company entities, and synthesizes a grounded report with citations.
/v1/video/info
Get video title, duration, thumbnail, and available quality options from YouTube, Twitter/X, TikTok, Instagram, Vimeo, LinkedIn, and 1700+ other platforms.
/v1/video/download
Download videos from YouTube, Twitter/X, TikTok, Instagram, Vimeo, LinkedIn, and 1700+ platforms. Returns a temporary pre-signed URL valid for 1 hour.
Python SDK
from suprsonic import Suprsonic
client = Suprsonic("omk_your_key")
# Convenience methods
result = client.search("latest AI news")
result = client.scrape("https://example.com")
result = client.verify_email("john@example.com")
result = client.emails.find(first_name="John", last_name="Doe", domain="example.com")
# Or use .run() for any capability
result = client.run("screenshot", url="https://example.com")TypeScript SDK
import { Suprsonic } from "suprsonic";
const client = new Suprsonic("omk_your_key");
const result = await client.search("latest AI news");
const result = await client.scrape("https://example.com");
const result = await client.verifyEmail("john@example.com");
// Or use .run() for any capability
const result = await client.run("screenshot", { url: "https://example.com" });Search the web and get AI-synthesized answers, raw Google SERP results, or both combined, with automatic provider routing.
Search the web with SERP, AI synthesis, or both
Parameters
query
Requiredstring
The search query.
num_results
number (default: 10)
Maximum number of organic results.
country
string (default: us)
ISO country code.
freshness
select (default: any)
Time filter.
Modes
The mode parameter is a preset that configures optimal provider routing for common use cases. You can also set individual parameters directly for fine-grained control.
Raw Google SERP results.
Links, snippets, knowledge graph. Fastest.
AI-synthesized answers with citations.
Coherent answer with source citations. 2-4s.
SERP + AI synthesis combined.
Raw sources plus synthesized answer. 3-6s.
Example response
{
"success": true,
"data": {
"answer": "AI funding reached record levels in Q1 2026. OpenAI closed a $110B round at $730B valuation, Anthropic raised $30B Series G at $380B, and xAI secured $20B.",
"citations": [],
"organic_results": [
{
"url": "https://techcrunch.com/2026/04/01/ai-funding",
"title": "AI Funding Hits Record in Q1",
"snippet": "Venture capital investment in AI startups reached unprecedented levels...",
"position": 1
}
],
"knowledge_graph": null,
"featured_snippet": null
},
"metadata": {
"provider_used": "perplexity",
"providers_tried": [
"perplexity"
],
"mode_used": "ai",
"response_time_ms": 7481,
"request_id": "req_48a34515"
},
"credits_used": 2
}Extract content from any URL with automatic escalation from fast HTTP fetch to JS rendering to stealth browser with CAPTCHA solving.
Extract content from any URL as Markdown or HTML
Parameters
url
Requiredstring
URL to scrape.
output
select (default: markdown)
Content format.
wait_for
string
CSS selector to wait for.
timeout
number (default: 30)
Max seconds.
Modes
The mode parameter is a preset that configures optimal provider routing for common use cases. You can also set individual parameters directly for fine-grained control.
Raw HTTP, no JS. <1s.
Static HTML only.
Full JS rendering. 2-5s.
SPAs, dynamic content.
Stealth browser + CAPTCHA. 10-30s.
Anti-bot sites.
Example response
{
"success": true,
"data": {
"content": "# Example Domain\n\nThis domain is for use in documentation examples.\n\n[Learn more](https://iana.org/domains/example)",
"title": "Example Domain",
"description": null,
"links": [
"https://iana.org/domains/example"
],
"screenshot_url": null
},
"metadata": {
"provider_used": "raw_http",
"providers_tried": [
"raw_http"
],
"mode_used": "fast",
"response_time_ms": 86,
"request_id": "req_10632882"
},
"credits_used": 1
}Find and enrich professional profiles by LinkedIn URL or name, with waterfall across multiple data providers and merged results.
Find and enrich professional profiles
Parameters
linkedin_url
string
LinkedIn profile URL.
first_name
string
First name.
last_name
string
Last name.
company
string
Company name.
include_image
boolean (default: true)
Fetch profile image.
Example response
{
"success": true,
"data": {
"first_name": "John",
"last_name": "Doe",
"full_name": "John Doe",
"headline": "CTO at Acme Corp",
"company": "Acme Corp",
"title": "Chief Technology Officer",
"location": "San Francisco, CA",
"summary": "Building the future of developer tools.",
"experience": [
{
"company": "Acme Corp",
"title": "CTO",
"start_date": "2022-01",
"end_date": null
}
],
"education": [],
"skills": [
"Python",
"Machine Learning",
"System Design"
],
"profile_image_url": "https://media.licdn.com/dms/image/...",
"linkedin_url": "https://linkedin.com/in/johndoe"
},
"metadata": {
"provider_used": "merged",
"providers_tried": [
"icypeas",
"leadmagic",
"exa"
],
"mode_used": null,
"response_time_ms": 4100,
"request_id": "req_ghi789"
},
"credits_used": 3
}Find verified professional email addresses by name and company domain.
Find professional email addresses
Parameters
first_name
Requiredstring
First name.
last_name
Requiredstring
Last name.
domain
Requiredstring
Company domain.
company
string
Company name (optional).
Example response
{
"success": true,
"data": {
"email": "jane@stripe.com",
"email_type": "professional",
"confidence": 0.95,
"verification_status": "verified",
"first_name": "Jane",
"last_name": "Smith",
"domain": "stripe.com"
},
"metadata": {
"provider_used": "icypeas",
"providers_tried": [
"icypeas"
],
"mode_used": null,
"response_time_ms": 22581,
"request_id": "req_29a74754"
},
"credits_used": 2
}Generate images from text prompts using Google GenAI with automatic fallback to DALL-E.
Generate images from text prompts
Parameters
prompt
Requiredstring
Image description.
aspect_ratio
select (default: 1:1)
Aspect ratio.
Example response
{
"success": true,
"data": {
"b64_json": "iVBORw0KGgoAAAANSUhEUg...(base64 image data)",
"content_type": "image/png",
"prompt": "A minimal blue circle on white background",
"aspect_ratio": "1:1",
"image_size": "512px"
},
"metadata": {
"provider_used": "google_genai",
"providers_tried": [
"google_genai"
],
"mode_used": null,
"response_time_ms": 9498,
"request_id": "req_2f408e4c"
},
"credits_used": 1
}Convert text to natural speech using Deepgram Aura with ElevenLabs fallback.
Convert text to speech audio
Parameters
text
Requiredstring
Text to convert (max 2000 chars).
voice_model
string
Deepgram voice model ID.
provider
select (default: auto)
TTS provider.
Example response
{
"success": true,
"data": {
"audio_base64": "//NkxAAc4FJgDHpMAQteDEe...(base64 audio data)",
"format": "mp3",
"sample_rate": 48000,
"text": "Hello, I am your AI assistant.",
"voice_model": "aura-2-thalia-en"
},
"metadata": {
"provider_used": "deepgram",
"providers_tried": [
"deepgram"
],
"mode_used": null,
"response_time_ms": 2582,
"request_id": "req_ba10d96a"
},
"credits_used": 2
}Transcribe audio via Deepgram with confidence scores and word-level timing.
Transcribe audio to text with timestamps
Parameters
audio_url
string
URL to audio file.
audio_base64
string
Base64-encoded audio.
language
string (default: en)
Language code.
Example response
{
"success": true,
"data": {
"transcript": "Yeah. As as much as, it's worth celebrating, the first spacewalk with an all female team, I think many of us are looking forward to it just being normal.",
"confidence": 0.99,
"language": "en",
"words": [
{
"word": "yeah",
"start": 0.08,
"end": 0.32,
"confidence": 0.99,
"punctuated_word": "Yeah."
},
{
"word": "as",
"start": 0.32,
"end": 0.8,
"confidence": 0.99,
"punctuated_word": "As"
}
],
"duration_seconds": 25.93
},
"metadata": {
"provider_used": "deepgram",
"providers_tried": [
"deepgram"
],
"mode_used": null,
"response_time_ms": 1607,
"request_id": "req_de622db0"
},
"credits_used": 2
}Generate sound effects, ambient audio, foley, and short instrumental music tracks from text descriptions. This is NOT text-to-speech: it does not produce spoken words. For voice/narration, use the tts capability instead.
Generate sound effects and short music tracks from text prompts (NOT speech: use tts for spoken voice)
Parameters
prompt
Requiredstring
Description of the sound effect or music to generate. NOT for speech (use tts for spoken voice).
duration_seconds
number (default: 5)
Length of generated audio in seconds (0.5 to 22). Leave unset to let the model auto-decide based on the prompt.
prompt_influence
number (default: 0.3)
How strictly to follow the prompt (0.0 = creative, 1.0 = literal). Default 0.3.
output_format
select (default: mp3_44100_128)
Audio format and quality.
Example response
{
"success": true,
"data": {
"audio_base64": "SUQzBAAAAAAAI1RTU0UAAAA...(base64 audio data)",
"format": "mp3",
"sample_rate": 44100,
"duration_seconds": 2,
"prompt": "short doorbell chime"
},
"metadata": {
"provider_used": "elevenlabs",
"providers_tried": [
"elevenlabs"
],
"mode_used": null,
"response_time_ms": 1500,
"request_id": "req_8bc6c1f9"
},
"credits_used": 4
}Send SMS messages reliably. WhatsApp available with recipient opt-in.
Send SMS or WhatsApp messages. Default channel is SMS (reliable delivery). WhatsApp requires recipient opt-in: they must have messaged your Business number within 24 hours.
Parameters
to
Requiredstring
Phone number (E.164).
message
Requiredstring
Message text.
channel
select (default: auto)
Delivery channel. Auto sends via SMS. WhatsApp requires opt-in: recipient must have messaged your Business number in the last 24 hours, otherwise the message is silently dropped by Meta.
Example response
{
"success": true,
"data": {
"message_id": "a361d2e2-3da4-4f5e-8a26-300e13cff0bf",
"channel": "sms",
"to": "+1234567890",
"from": "+15551234567",
"status": "sent"
},
"metadata": {
"provider_used": "twilio",
"providers_tried": [
"twilio"
],
"mode_used": null,
"response_time_ms": 350,
"request_id": "req_yza567"
},
"credits_used": 1
}Extract structured data using LLM-powered analysis with a user-defined schema.
Extract structured data from URLs or content
Parameters
url
string
URL to scrape and extract from.
content
string
Pre-scraped text content.
extraction_prompt
Requiredstring
What to extract (required unless schema is provided).
schema
string
JSON schema for extraction.
Example response
{
"success": true,
"data": {
"extracted": {
"main_heading": "Example Domain",
"links": [
{
"text": "Learn more",
"url": "https://iana.org/domains/example"
}
]
},
"source_url": "https://example.com",
"content_length": 167,
"truncated": false
},
"metadata": {
"provider_used": "llm_extraction",
"providers_tried": [
"llm_extraction"
],
"mode_used": null,
"response_time_ms": 1716,
"request_id": "req_bc82d469"
},
"credits_used": 3
}Enrich company data with firmographics from Apollo, brand identity from BrandFetch, and qualitative analysis via LLM.
Enrich company data by domain
Parameters
domain
Requiredstring
Company domain.
company_name
string
Optional name hint.
Example response
{
"success": true,
"data": {
"company_name": "Stripe",
"domain": "stripe.com",
"description": "Stripe, Inc. is a financial infrastructure platform founded in 2010 by brothers John and Patrick Collison.",
"industry": "information technology & services",
"company_size": "5000+",
"founded_year": 2010,
"headquarters": "South San Francisco, California, United States",
"employees": 8000,
"annual_revenue": 5120000000,
"annual_revenue_printed": "5.1B",
"total_funding": 9429289778,
"total_funding_printed": "9.4B",
"latest_funding_stage": "Venture (Round not Specified)",
"publicly_traded_symbol": null,
"publicly_traded_exchange": null,
"twitter_handle": "@stripe",
"linkedin_handle": "http://www.linkedin.com/company/stripe",
"social_links": {
"twitter": "http://twitter.com/stripe",
"linkedin": "http://www.linkedin.com/company/stripe",
"facebook": "https://www.facebook.com/StripeHQ"
},
"website": "http://www.stripe.com",
"technology_names": [
".NET",
"Amazon AWS",
"React",
"Ruby On Rails",
"Python"
],
"primary_brand_color": "#635BFF",
"secondary_brand_color": null,
"logo_url": "https://cdn.brandfetch.io/idxAg10C0L/theme/light/logo.svg",
"icon_url": "https://cdn.brandfetch.io/idxAg10C0L/w/480/h/480/theme/dark/icon.jpeg",
"instagram_handle": "@stripehq",
"company_kind": "PRIVATELY_HELD",
"is_claimed": true,
"value_proposition": "A reliable, flexible financial infrastructure that allows businesses to accept payments and offer financial services.",
"ideal_customers": "Businesses of all sizes, from startups to large global enterprises."
},
"metadata": {
"provider_used": "merged",
"providers_tried": [
"apollo",
"brandfetch",
"website_analysis"
],
"mode_used": null,
"response_time_ms": 4486,
"request_id": "req_8620be37"
},
"credits_used": 3
}Check if an email is deliverable, catch-all, or disposable.
Check if an email is deliverable, catch-all, or disposable
Parameters
string
Email to verify.
Example response
{
"success": true,
"data": {
"email": "john@example.com",
"status": "valid",
"sub_status": "",
"is_free_email": false,
"did_you_mean": null,
"domain_age_days": "724",
"smtp_provider": "g-suite",
"mx_found": "true",
"mx_record": "aspmx.l.google.com"
},
"metadata": {
"provider_used": "zerobounce",
"providers_tried": [
"zerobounce"
],
"mode_used": null,
"response_time_ms": 416,
"request_id": "req_c571c4d7"
},
"credits_used": 1
}Transcribe audio/video with speaker diarization and timestamps.
Transcribe audio with speaker diarization and timestamps
Parameters
audio_url
Requiredstring
URL to audio/video file.
language
string (default: en_us)
Language code.
speaker_labels
boolean (default: true)
Enable speaker diarization.
Example response
{
"success": true,
"data": {
"transcript": "Yeah. As as much as, it's worth celebrating, the first spacewalk with an all female team, I think many of us are looking forward to it just being normal.",
"confidence": 0.99,
"language": "en",
"duration_seconds": 25.93,
"word_count": 62,
"speaker_count": 1,
"utterances": [
{
"speaker": 0,
"text": "Yeah. As as much as, it's worth celebrating,",
"start": 0.08,
"end": 3.3,
"confidence": 0.99
},
{
"speaker": 0,
"text": "the first, spacewalk,",
"start": 4.48,
"end": 5.78,
"confidence": 0.94
}
]
},
"metadata": {
"provider_used": "deepgram",
"providers_tried": [
"deepgram"
],
"mode_used": null,
"response_time_ms": 1361,
"request_id": "req_16129e15"
},
"credits_used": 3
}Extract line items, totals, dates from invoices and receipts.
Extract structured data from invoices and receipts
Parameters
document_url
Requiredstring
URL to invoice PDF/image.
Example response
{
"success": true,
"data": {
"invoice_number": "INV-2026-0042",
"date": "2026-04-15",
"due_date": "2026-05-15",
"supplier_name": "Acme Services LLC",
"supplier_address": "123 Main St, San Francisco, CA 94102",
"customer_name": "Widget Corp",
"currency": "USD",
"subtotal": 250,
"total_tax": 49.99,
"total_amount": 299.99,
"line_items": [
{
"description": "Consulting services (10 hrs)",
"quantity": 10,
"unit_price": 25,
"total_amount": 250,
"tax_rate": 0.2
}
]
},
"metadata": {
"provider_used": "gemini",
"providers_tried": [
"gemini"
],
"mode_used": null,
"response_time_ms": 4200,
"request_id": "req_nop012"
},
"credits_used": 3
}Generate SRT/VTT subtitles from audio or video files.
Generate SRT/VTT subtitles from audio or video
Parameters
audio_url
Requiredstring
URL to audio/video.
language
string (default: en)
Language code.
format
select (default: srt)
Subtitle format.
Example response
{
"success": true,
"data": {
"subtitle_content": "1\n00:00:00,080 --> 00:00:03,299\nYeah. As as much as, it's worth celebrating,\n\n2\n00:00:04,480 --> 00:00:05,779\nthe first, spacewalk,\n\n3\n00:00:06,319 --> 00:00:07,859\nwith an all female team,",
"format": "srt",
"language": "en",
"duration_seconds": 25.93,
"utterance_count": 8
},
"metadata": {
"provider_used": "deepgram",
"providers_tried": [
"deepgram"
],
"mode_used": null,
"response_time_ms": 1473,
"request_id": "req_55f379a5"
},
"credits_used": 2
}Convert files between 200+ formats (PDF, DOCX, XLSX, images).
Convert files between 200+ formats
Parameters
file_url
Requiredstring
URL to source file.
source_format
Requiredstring
Source format.
target_format
string (default: pdf)
Target format.
Example response
{
"success": true,
"data": {
"file_name": "example_com.pdf",
"file_size": 16246,
"file_url": "https://v2.convertapi.com/d/4kkovcg6keh.../example_com.pdf",
"conversion_cost": 1,
"source_format": "web",
"target_format": "pdf"
},
"metadata": {
"provider_used": "convertapi",
"providers_tried": [
"convertapi"
],
"mode_used": null,
"response_time_ms": 1175,
"request_id": "req_ed9cc6d5"
},
"credits_used": 2
}Remove background from any image using AI segmentation.
Remove background from any image. Returns transparent PNG.
Parameters
image_url
Requiredstring
URL to image.
size
select (default: auto)
Output resolution.
Example response
{
"success": true,
"data": {
"image_base64": "iVBORw0KGgoAAAANSUhEUg...(base64 PNG with transparent background)",
"format": "png",
"content_type": "image/png"
},
"metadata": {
"provider_used": "rembg",
"providers_tried": [
"rembg"
],
"mode_used": null,
"response_time_ms": 8500,
"request_id": "req_4fd62009"
},
"credits_used": 2
}Capture a rendered screenshot of any webpage.
Capture a rendered screenshot of any webpage
Parameters
url
Requiredstring
URL to capture.
width
number (default: 1280)
Viewport width.
height
number (default: 720)
Viewport height.
format
select (default: png)
Output format.
full_page
boolean (default: false)
Capture full scrollable page.
Example response
{
"success": true,
"data": {
"image_base64": "iVBORw0KGgoAAAANSUhEUg...(base64 image data)",
"format": "png",
"width": 1280,
"height": 720,
"full_page": false,
"size_bytes": 6325
},
"metadata": {
"provider_used": "anchor",
"providers_tried": [
"anchor"
],
"mode_used": null,
"response_time_ms": 6753,
"request_id": "req_70d8a7af"
},
"credits_used": 1
}Execute Python, JavaScript, or shell code in an isolated Firecracker microVM sandbox.
Execute code in a secure sandbox with pre-configured environments
Parameters
code
Requiredstring
The code to execute.
language
select (default: python)
Programming language.
timeout
number (default: 30)
Max execution time (1-300s).
template
select (default: default)
Pre-configured environment.
Example response
{
"success": true,
"data": {
"stdout": "Hello from Python 3.13\n",
"stderr": "",
"exit_code": 0,
"execution_time_ms": 730,
"output_files": [],
"sandbox_boot_ms": 537,
"template_used": "default"
},
"metadata": {
"provider_used": "e2b",
"providers_tried": [
"e2b"
],
"mode_used": null,
"response_time_ms": 2085,
"request_id": "req_50b9c743"
},
"credits_used": 2
}Get WHOIS, DNS records, SSL analysis, technology fingerprinting, email security, and hosting data for any domain in one call.
Get comprehensive domain intelligence: WHOIS, DNS, SSL, tech stack, email security, hosting
Parameters
domain
Requiredstring
Domain to analyze (e.g. stripe.com).
mode
select (default: overview)
Intelligence depth.
Modes
The mode parameter is a preset that configures optimal provider routing for common use cases. You can also set individual parameters directly for fine-grained control.
All signals combined.
WHOIS + DNS + SSL + hosting + email security.
Registration data.
Registrar, dates, nameservers, DNSSEC.
Full record dump + email security.
A, MX, NS, TXT, SPF/DMARC/DKIM.
Technology fingerprinting.
CDN, frameworks, CMS, analytics from headers+HTML.
Security posture with A-F grade.
SSL + email security + HTTP headers scored.
Subdomain discovery.
DNS brute force for 40+ common patterns.
Example response
{
"success": true,
"data": {
"domain": "stripe.com",
"whois": {
"created": "1995-09-12",
"expires": "2027-09-11",
"updated": "2025-10-01",
"registrar": "SafeNames Ltd.",
"nameservers": [
"NS-1087.AWSDNS-07.ORG",
"NS-1882.AWSDNS-43.CO.UK",
"NS-423.AWSDNS-52.COM",
"NS-705.AWSDNS-24.NET"
],
"status": [
"client delete prohibited",
"client transfer prohibited"
],
"dnssec": false,
"source": "rdap"
},
"dns": {
"provider": "AWS Route 53",
"a_records": [
"54.76.53.164",
"52.215.231.162"
],
"mx_records": [
{
"priority": 10,
"host": "aspmx.l.google.com"
},
{
"priority": 20,
"host": "alt2.aspmx.l.google.com"
}
],
"email_provider": "Google Workspace",
"has_spf": true,
"spf_record": "v=spf1 ip4:198.2.180.60/32 include:spf1.stripe.com ~all",
"has_dmarc": true,
"dmarc_policy": "reject",
"dkim_found": true,
"dkim_selectors": [
{
"selector": "google",
"preview": "v=DKIM1; k=rsa; p=MIGfMA0G..."
}
]
},
"ssl": {
"issuer": "DigiCert Inc",
"valid_to": "2026-07-02",
"days_until_expiry": 65,
"protocol": "TLSv1.3",
"cipher_suite": "TLS_AES_256_GCM_SHA384"
},
"hosting": {
"provider": "Nginx",
"confidence": "medium",
"ip": "54.76.53.164",
"asn": "AS16509",
"asn_org": "Amazon.com, Inc.",
"country": "IE",
"city": "Dublin"
}
},
"metadata": {
"provider_used": "multi",
"providers_tried": [
"rdap",
"dnspython",
"ssl",
"ipinfo"
],
"mode_used": null,
"response_time_ms": 2721,
"request_id": "req_dc74a442"
},
"credits_used": 2
}Deep research that searches the web, scrapes full content, enriches people and company entities, and synthesizes a grounded report with citations.
Multi-step deep research: search, scrape, enrich entities, and synthesize into a cited report
Parameters
query
Requiredstring
The research question or objective.
depth
select (default: standard)
Research depth.
enrich_entities
boolean (default: true)
Enrich detected people and companies with profile and firmographic data.
include_analysis
boolean (default: false)
Generate computational analysis with charts.
synthesis
boolean (default: true)
Generate a synthesized report. Set false for raw mode (sources + entities only).
source_types
string (default: web)
Comma-separated source types: web, news, academic.
max_sources
number (default: 15)
Maximum number of sources to collect.
freshness
select (default: any)
Time filter for search results.
Modes
The mode parameter is a preset that configures optimal provider routing for common use cases. You can also set individual parameters directly for fine-grained control.
Quick research, up to 5 searches and 8 scrapes.
Fast research for factual questions. 30-60s.
Thorough research with refinement.
Multi-angle research with gap analysis. 1-3 min.
Exhaustive research with iterative refinement.
Maximum depth, up to 30 searches and 40 scrapes. 3-8 min.
Example response
{
"success": true,
"data": {
"report": {
"title": "AI Chip Startups Competing with Nvidia (2026)",
"summary": "Several startups are challenging Nvidia's dominance in AI accelerators...",
"sections": [
{
"heading": "Market Overview",
"content": "The AI chip market is projected to reach $120B by 2030 [Source 1]..."
}
],
"key_findings": [
"Cerebras and Groq lead in inference speed",
"Custom silicon adoption growing 40% YoY"
],
"confidence": 0.85
},
"sources": [
{
"id": 1,
"url": "https://techcrunch.com/2026/ai-chips",
"title": "AI Chip Race Heats Up",
"domain": "techcrunch.com",
"snippet": "Startups are racing to challenge Nvidia...",
"source_type": "web"
}
],
"entities": {
"people": [
{
"name": "Jensen Huang",
"role": "CEO",
"company": "Nvidia"
}
],
"companies": [
{
"name": "Cerebras",
"domain": "cerebras.net",
"industry": "AI Hardware",
"employee_count": 500
}
]
},
"metadata": {
"depth_used": "standard",
"sources_searched": 4,
"sources_scraped": 5,
"sources_cited": 5,
"entities_enriched": 2,
"refinement_rounds": 0,
"budget_exhausted": false,
"total_time_ms": 35000,
"steps_completed": [
"query_expansion",
"web_search",
"content_extraction",
"entity_detection",
"entity_enrichment",
"synthesis"
]
}
},
"metadata": {
"provider_used": "research_orchestrator",
"providers_tried": [
"research_orchestrator"
],
"mode_used": "standard",
"response_time_ms": 35000,
"request_id": "req_abc123"
},
"credits_used": 10
}Get video title, duration, thumbnail, and available quality options from YouTube, Twitter/X, TikTok, Instagram, Vimeo, LinkedIn, and 1700+ other platforms.
Extract video metadata, available formats, and thumbnail from any URL
Parameters
url
Requiredstring
URL of the video or post containing a video.
Example response
{
"success": true,
"data": {
"title": "Example Video Title",
"duration_seconds": 245,
"thumbnail_url": "https://i.ytimg.com/vi/dQw4w9WgXcQ/maxresdefault.jpg",
"uploader": "ExampleChannel",
"upload_date": "2026-01-15",
"view_count": 1500000,
"platform": "youtube",
"formats": [
{
"quality": "1080p",
"format_id": "137+140",
"ext": "mp4",
"filesize_mb": 45.2
},
{
"quality": "720p",
"format_id": "136+140",
"ext": "mp4",
"filesize_mb": 22.1
},
{
"quality": "480p",
"format_id": "135+140",
"ext": "mp4",
"filesize_mb": 12.8
},
{
"quality": "audio_only",
"format_id": "140",
"ext": "m4a",
"filesize_mb": 3.9
}
]
},
"metadata": {
"provider_used": "yt_dlp",
"providers_tried": [
"yt_dlp"
],
"response_time_ms": 2100,
"request_id": "req_v1d30info"
},
"credits_used": 1
}Download videos from YouTube, Twitter/X, TikTok, Instagram, Vimeo, LinkedIn, and 1700+ platforms. Returns a temporary pre-signed URL valid for 1 hour.
Download video from any URL and return a temporary download link
Parameters
url
Requiredstring
URL of the video or post containing a video.
quality
select (default: 720)
Desired video quality (best available up to this resolution).
format
select (default: mp4)
Output format.
Modes
The mode parameter is a preset that configures optimal provider routing for common use cases. You can also set individual parameters directly for fine-grained control.
Download as MP4 video.
Full video+audio merged into MP4. 5-60s depending on length.
Extract audio only.
Audio track as MP3 or M4A. Faster, smaller file.
Example response
{
"success": true,
"data": {
"download_url": "https://cdn.example.com/downloads/abc123.mp4?X-Amz-Signature=...",
"expires_at": "2026-05-03T14:30:00Z",
"filename": "Example_Video_Title.mp4",
"filesize_mb": 22.1,
"duration_seconds": 245,
"quality": "720p",
"format": "mp4",
"title": "Example Video Title",
"thumbnail_url": "https://i.ytimg.com/vi/dQw4w9WgXcQ/maxresdefault.jpg"
},
"metadata": {
"provider_used": "yt_dlp",
"providers_tried": [
"yt_dlp"
],
"response_time_ms": 12500,
"request_id": "req_v1d30dl"
},
"credits_used": 3
}