Audio Transcribe API

Transcribes audio to text with whisper-large-v3.

Overview

Transcribes audio to text with whisper-large-v3. Server-side fetches the audio URL (max 25 MB), relays it to Venice's audio/transcriptions endpoint, and returns the transcript with detected language, duration, and per-segment timestamps when response_format='verbose_json' (default). Also supports raw text, SRT, and VTT outputs. Use it as a speech-to-text or multi-language ASR endpoint with OpenAI Whisper API compatibility.

Endpoint

Method	Endpoint	Price	Description
POST	/v1/marketplace/api/audio-transcribe	$0.0115	Invoke Audio Transcribe (Document) and return the upstream response.

How to call it

Requests are paid per call over the x402 protocol. Call the endpoint, receive a 402 Payment Required quote, then repeat the request with the signed payment header. The SDKs do both steps for you.

# 1. Ask for a quote
curl -i -X POST https://jarvisclaw.ai/v1/marketplace/api/audio-transcribe \
  -H 'Content-Type: application/json' \
  -d '{}'

# 2. Pay it (the SDK signs and retries for you)
curl -X POST https://jarvisclaw.ai/v1/marketplace/api/audio-transcribe \
  -H 'Content-Type: application/json' \
  -H 'X-PAYMENT: <signed-payload>' \
  -d '{}'

Parameters

Taken from the request example this API publishes.

Name	In	Type	Example
audio_url	body	string	"https://download.samplelib.com/mp3/sample-3s.mp3"
language	body	string	"auto"

Example response

{
  "transcript": "Now is the time for all good men to come to the aid of their country.",
  "language_detected": "en",
  "duration_seconds": 4.21,
  "segments": [
    {
      "id": 0,
      "start": 0,
      "end": 4.21,
      "text": "Now is the time for all good men to come to the aid of their country."
    }
  ],
  "response_format": "verbose_json",
  "model": "openai/whisper-large-v3",
  "bytes_in": 142311,
  "source": "venice"
}

FAQ

How much does the Audio Transcribe API cost?

$0.0115 USDC per call, paid per call over x402. There is no subscription, minimum or monthly fee.

Do I need an API key?

No. Call the endpoint, read the 402 Payment Required quote, and repeat the request with a signed USDC payment header. An account API key also works if you prefer prepaid billing.

Which chains can I pay on?

USDC on Base or on Solana. The 402 quote lists the accepted networks and the exact amount; the JarvisClaw SDKs sign and retry for you.

How do I call it from an AI agent?

Send POST to the endpoint above from any HTTP client, or connect the JarvisClaw MCP server and let the agent find and call it with the search_apis and get_api_detail tools.

Related APIs

• Pdf To Markdown
• Convert Pdf
• Video To Text
• Video Transcribe
• Video To Audio

Open in the marketplace