Proxy Audio Transcribe
by Speech to Text Transcription (Wh in AI models & inference
Speech to text for agents: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds.
https://agentsvc.io/api/v1/proxy/audio-transcribe- Price
- $0.01
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 162 ms
- 206 ms slowest 5%
- Last check
- Passed
- 4 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://agentsvc.io/api/v1/proxy/audio-transcribe
Each call costs $0.01 in USDC on Polygon, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://agentsvc.io/api/v1/proxy/audio-transcribe
content-type: application/json
{
"audio_url": "https://agentsvc.io/samples/speech-en.mp3"
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
audio_base64 | string | No | Audio file as base64; or use audio_url |
audio_url | string | No | Public URL of the audio file |
language | string | No | ISO 639-1 code like en or de, default auto-detect |
model | string | No | small is more accurate, base about twice as fast One of: small, base. Default: "small". |
timestamps | boolean | No | Include segments with start and end seconds Default: true. |
Example response
The provider's example. We can't check it without paying.
{
"data": {
"duration_seconds": 9.17,
"language": "en",
"language_probability": 0.998,
"model": "whisper-small",
"model_license": "MIT (OpenAI Whisper weights, faster-whisper runtime), runs on agentsvc.io, audio is deleted after the call",
"processing_ms": 3688,
"segments": [
{
"end": 4.4,
"start": 0,
"text": "This is a sample recording for the agents.io speech to text service."
},
{
"end": 9,
"start": 4.4,
"text": "It turns spoken audio into text with time stamps in about 100 languages."
}
],
"text": "This is a sample recording for the agents.io speech to text service. It turns spoken audio into text with time stamps in about 100 languages."
},
"success": true
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.01.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://agentsvc.io/api/v1/proxy/audio-transcribe' \
-H 'content-type: application/json' \
--data-raw '{"audio_url":"https://agentsvc.io/samples/speech-en.mp3"}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://agentsvc.io/api/v1/proxy/audio-transcribe' \
-H 'content-type: application/json' \
--data-raw '{"audio_url":"https://agentsvc.io/samples/speech-en.mp3"}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.01 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.01" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.01 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagentsvc.io%2Fapi%2Fv1%2Fproxy%2Faudio-transcribe&method=POST
const res = await pay("https://agentsvc.io/api/v1/proxy/audio-transcribe", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"audio_url": "https://agentsvc.io/samples/speech-en.mp3"
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.01 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.01"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://agentsvc.io/api/v1/proxy/audio-transcribe",
json={
"audio_url": "https://agentsvc.io/samples/speech-en.mp3",
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 4 h ago | Passed | 402 | 163 ms | $0.01 |
| 9 h ago | Passed | 402 | 113 ms | $0.01 |
| 14 h ago | Passed | 402 | 33 ms | $0.01 |
| 18 h ago | Passed | 402 | 206 ms | $0.01 |
| 23 h ago | Passed | 402 | 202 ms | $0.01 |
Show 4 older checks
| 28 h ago | Passed | 402 | 187 ms | $0.01 |
| 32 h ago | Passed | 402 | 162 ms | $0.01 |
| 37 h ago | Passed | 402 | 109 ms | $0.01 |
| 47 h ago | Passed | 402 | 34 ms | $0.01 |