"Your order shipped this morning."
POST /v1/audio/speech
Text to speech
Clear, natural speech returned as a whole file or streamed while it is generated, so playback starts right away.
Speech docsLow-latency speech-to-text and text-to-speech APIs with transcripts you can rely on, proven in clinical, contact-center and voice-agent workflows.
Hi, I'm Clara. I can confirm your appointment, answer billing questions, or connect you with a nurse.
Unedited output from the API. Pick a voice and press play.
Products
Transcribe live or recorded audio, and generate speech that streams as it is produced. One key, one bill, one set of logs.
"Your order shipped this morning."
POST /v1/audio/speech
Clear, natural speech returned as a whole file or streamed while it is generated, so playback starts right away.
Speech docsSo the plan is to ship the beta on Friday.
POST /v1/audio/transcriptions
Upload a recording and get an accurate transcript back, or stream live audio over a WebSocket and get the words while people are still talking.
Speech to speech
One model that listens and answers in voice, without a transcription step in between. For the most natural, lowest-latency conversations.
Get early accessWhy xVoice
Three things voice teams usually have to trade against each other. xVoice gives you all of them through one API.
Transcripts arrive while the person is still speaking, and speech starts playing before the full reply is generated. Nobody waits in silence.
Drug names, dosages and lab values come out as they were said, on real call audio as well as clean recordings.
HIPAA compliant with a BAA available, and SOC 2 Type II audited. Your security review doesn't stall on us.
Security and complianceWorkflows
xVoice runs where errors are expensive and delays are noticed: in clinics, contact centers and customer-facing voice agents.
Ambient scribing and dictation that turn visits into accurate notes, with medications, dosages and findings captured correctly.
Live agent assist while the customer is still talking, and quality review on every call instead of a sample.
Scheduling, intake and support agents that hear the caller and answer without the pauses that make people hang up.
Searchable transcripts of recorded calls and consultations for audits, disputes and regulatory review.
Security and compliance
Healthcare and enterprise teams can put xVoice into production without a compliance detour.
Process protected health information through xVoice. We sign a Business Associate Agreement with covered entities and their partners.
BAA available
Our security controls are independently audited. The report is available to customers and prospects under NDA.
Developer experience
The xVoice API follows the OpenAI audio API, so there is no new SDK to learn. Already on OpenAI? Change the base URL and the key, and your code runs on xVoice.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openai.com/v1",
api_key=os.environ["OPENAI_API_KEY"],
base_url="https://api.xvoice.dev/v1",
api_key=os.environ["XVOICE_API_KEY"],
)
with open("call.wav", "rb") as audio:
transcript = client.audio.transcriptions.create(
model="cadence-stt",
file=audio,
)
print(transcript.text)import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openai.com/v1",
apiKey: process.env.OPENAI_API_KEY,
baseURL: "https://api.xvoice.dev/v1",
apiKey: process.env.XVOICE_API_KEY,
});
const speech = await client.audio.speech.create({
model: "cadence-tts",
voice: "clara",
input: "Hello from xVoice.",
});
await fs.promises.writeFile("hello.mp3", Buffer.from(await speech.arrayBuffer()));curl https://api.xvoice.dev/v1/audio/speech \
-H "Authorization: Bearer $XVOICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cadence-tts",
"voice": "clara",
"input": "Hello from xVoice.",
"response_format": "mp3"
}' \
-o hello.mp3Platform
The dashboard your team needs on day one: keys, logs, usage and spend, all scoped by organization and project.
Separate keys per app and environment, test or live. Revoke one without touching the rest.
Every call has a request id that ties an invoice line to a row in your logs, errors included.
Seconds of audio and characters of text, grouped by project, model or key, over any range.
Pay as you go from a balance. Auto-recharge keeps it topped up; nothing bills you by surprise.
Cap what a month can cost. Rate limit headers on every metered call tell you where you stand.
Invite people by email with roles. Every change to keys, members or spending is recorded.
Requests
clinic-intake · live
Requests
12,480
Audio
41.2 h
Characters
2.9M
| POST | /v1/audio/speech | cadence-tts | 200 | 312 ms |
| WS | /v1/realtime | cadence-stt | 101 | 14m 02s |
| POST | /v1/audio/transcriptions | cadence-stt | 200 | 1.84 s |
| POST | /v1/audio/speech | cadence-tts | 200 | 296 ms |
| POST | /v1/audio/speech | cadence-tts | 400 | 9 ms |
Pricing
Start free, then pay as you go from prepaid credits. No subscriptions, no minimums, no commitments.
Speech to textcadence-stt
Accurate transcripts of recorded audio. Billed for the exact duration of each file, never rounded up to the minute.
$0.03/ hr
Realtime speech to textcadence-stt
Live audio over a WebSocket, with words back while people are still talking. Billed per second of audio streamed.
$0.25/ hr
Text to speechcadence-tts
Natural speech as a whole file or streamed as it is generated. Billed per character of input.
$4/ 1M chars
Custom
Custom
Get volume pricing, custom rate limits and concurrency, and a signed BAA for PHI, tailored to your voice workloads.
Contact salesFAQ
Yes. You can process protected health information through xVoice, and we sign a Business Associate Agreement with covered entities and their business associates. Get in touch to start one.
Yes, SOC 2 Type II. The report is available to customers and prospects under NDA.
No. The API follows the OpenAI audio API, so the official Python and Node clients work unchanged. Point them at the xVoice base URL with an xVoice key.
Prepaid credit, deducted per second of audio transcribed and per character of speech generated. Verifying your email adds $5 of free credit. Top-ups run from $5 to $1,000, auto-recharge is optional, and a monthly spending cap protects you from runaway usage.
Limits are per organization, covering requests per minute, concurrent requests, characters and audio seconds. Every metered response carries headers showing where you stand, and limits can be raised for production workloads.
Still have questions? Talk to us →
Start with free credit and make your first call in minutes, or talk to us about a BAA and volume pricing.