Saylor Innovations Agent Bazaar by Saylor Innovations
Connect an Agent
mirrored listing x402 eip155:8453

Speech-to-text transcription for voice messages and audio clips

Speech-to-text transcription for voice messages and audio clips. Upload a wav, mp3, m4a, ogg or webm file as multipart form-data and get the spoken text back as JSON. Runs a dedicated ASR model, so short noisy voice notes transcribe accurately. Accepts clips up to 10 minutes / 25 MB, billed per 10-second block. Use it to turn voice notes, call recordings, podcast clips or voicemail into text an agent can read.

Do you run voice.cyberwarex.com? This listing was mirrored from Coinbase's public Bazaar. Claim it in 30 seconds — no account required — and it becomes verified, permanently overriding the mirrored copy.

Claim this listing
15000 (raw units)
price
15
calls / 30d
1
unique payers
2026-09-01
updated

Provider

voice.cyberwarex.com · discovered, not yet claimed by its owner

Payment (x402 accepts[])

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0x058D0Cc5CC97e61e8A9f38D6d6365bce525921B2",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "15000",
    "maxTimeoutSeconds": 300
  }
]

Output schema

{
  "bazaar": {
    "info": {
      "input": {
        "body": {
          "file": "<multipart audio file: voice-note.mp3>"
        },
        "bodyType": "form-data",
        "method": "POST",
        "type": "http"
      },
      "output": {
        "example": {
          "text": "Hey, quick voice note about the Q3 roadmap. Can we move the launch review to Thursday?"
        },
        "type": "json"
      }
    },
    "schema": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "input": {
          "additionalProperties": false,
          "properties": {
            "body": {
              "properties": {
                "file": {
                  "description": "Audio file to transcribe (wav, mp3, m4a, ogg, webm, flac). Max 10 minutes and 25 MB.",
                  "format": "binary",
                  "type": "string"
                }
              },
              "required": [
                "file"
              ],
              "type": "object"
            },
            "bodyType": {
              "enum": [
                "json",
                "form-data",
                "text"
              ],
              "type": "string"
            },
            "method": {
              "enum": [
                "POST",
                "PUT",
                "PATCH"
              ],
              "type": "string"
            },
            "type": {
              "const": "http",
              "type": "string"
            }
          },
          "required": [
            "type",
            "method",
            "bodyType",
            "body"
          ],
          "type": "object"
        },
        "output": {
          "properties": {
            "example": {
              "properties": {
                "charged": {
                  "description": "False when silence was detected and no payment was taken.",
                  "type": "boolean"
                },
                "note": {
                  "description": "Set to 'no speech detected' when the clip is silent.",
                  "type": "string"
                },
                "text": {
                  "description": "Transcribed speech from the uploaded audio.",
                  "type": "string"
                }
              },
              "type": "object"
            },
            "type": {
              "type": "string"
            }
          },
          "required": [
            "type"
          ],
          "type": "object"
        }
      },
      "required": [
        "input"
      ],
      "type": "object"
    }
  }
}

Use it

curl

curl "https://voice.cyberwarex.com/transcribe"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

JavaScript

const res = await fetch("https://voice.cyberwarex.com/transcribe");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

Python

import httpx
res = httpx.get("https://voice.cyberwarex.com/transcribe")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Machine-readable

Everything on this page is also available as clean JSON at /resources/8356.json, and this resource appears in /discovery/resources and /discovery/search.