Audio Speech
by Telnyx Inference in AI models & inference
Text-to-speech (OpenAI-compatible /v1/audio/speech). 4,358 voices across 9 providers (KokoroTTS, AWS Polly, Azure, MiniMax, more — free catalog at GET /v1/audio/voices). Returns mp3. Up to 3000 chars. $0.000006 USDC per character (Telnyx list rate, zero margin): pay per character via the upto scheme (min $0.002 network settlement floor, so ≤333-char calls settle at $0.002), or flat $0.018 exact.
https://x402.telnyx.com/v1/audio/speech- Price
- $0.018
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 220 ms
- 230 ms slowest 5%
- Last check
- Passed
- 2 h ago, next any minute now
Reliability
How to call it
POST https://x402.telnyx.com/v1/audio/speech
Each call costs $0.018 in USDC on Base, 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://x402.telnyx.com/v1/audio/speech
content-type: application/json
{
"input": "Hello from the Telnyx x402 gateway.",
"model": "tts-1",
"voice": "alloy"
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
input | string | Yes | Text to synthesize (max 3000 characters). |
model | string | No | Accepted for OpenAI SDK compatibility; the voice id selects the engine. |
response_format | string | No | One of: mp3. |
voice | string | Yes | OpenAI voice name (alloy, echo, fable, onyx, nova, shimmer, …) or Telnyx voice id (Provider.Model.VoiceId). Full catalog: GET /v1/audio/voices. |
Example response
The provider's example. We can't check it without paying.
{
"body": "<binary mp3 bytes of the synthesized speech>",
"content_type": "audio/mpeg"
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.018.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://x402.telnyx.com/v1/audio/speech' \
-H 'content-type: application/json' \
--data-raw '{"input":"Hello from the Telnyx x402 gateway.","model":"tts-1","voice":"alloy"}'
# 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://x402.telnyx.com/v1/audio/speech' \
-H 'content-type: application/json' \
--data-raw '{"input":"Hello from the Telnyx x402 gateway.","model":"tts-1","voice":"alloy"}' \
| 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 $0.018 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.018" });
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 $0.018 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.telnyx.com%2Fv1%2Faudio%2Fspeech&method=POST
const res = await pay("https://x402.telnyx.com/v1/audio/speech", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"input": "Hello from the Telnyx x402 gateway.",
"model": "tts-1",
"voice": "alloy"
}),
});
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 $0.018 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.018"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://x402.telnyx.com/v1/audio/speech",
json={
"input": "Hello from the Telnyx x402 gateway.",
"model": "tts-1",
"voice": "alloy",
},
)
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 |
|---|---|---|---|---|
| 2 h ago | Passed | 402 | 220 ms | $0.018 |
| 6 h ago | Passed | 402 | 230 ms | $0.018 |
| 11 h ago | Passed | 402 | 153 ms | $0.018 |
| 15 h ago | Passed | 402 | 473 ms | $0.018 |