Official API Documentation

Developer Docs

Integrate realistic text-to-speech (TTS) and voice cloning capabilities into your apps via standard RESTful endpoints.

Overview

Khmer Vox TTS exposes audio endpoints backed by VoxCPM. For production apps and business customers, use clone voice with a reference audio sample because normal VoxCPM speech can change speaker between generations. Every speech and clone submission creates a queued job and returns a job ID immediately — poll the job, then download the result as WAV audio or a ZIP of per-line WAV files.

Try API Console Create API Key

Production path

Text to Speech

POST

/api/v1/audio/speech

TTS for any text length. Returns job ID immediately, poll for audio. No timeout issues.

Batch TTS

POST

/api/v1/audio/batch

Multiple lines in one job. Poll status, download merged WAV or ZIP.

Clone Voice

POST

/api/v2/audio/clone/jobs

Async voice clone with reference audio. Returns job ID, poll for result.

Base URL

https://voxtts.online

Authentication

Query param (?api_key=) or Bearer <REDACTED>

Output

Async job-based: poll status, download WAV/ZIP

Get started

Quickstart

Buy tokens

1Create an account or sign in.
2Buy Creator, Pro, or a paid token pack from Billing. Free accounts cannot create or use API keys.
3Open Dashboard > API and create an API key. Daily and monthly limits are optional.
4Call the TTS endpoint with your API key as a query parameter. Returns a job ID immediately — poll for the result.

Dubbing integration

Use this setup for video dubbing tools

Dubbing systems should use clone voice with a reference speaker sample. Do not depend on a named voice for business work because normal VoxCPM speech can change speaker between calls.

Test multipart clone

1. First live test

Call /api/v2/audio/clone/jobs with multipart/form-data. Send sample as a file, input as speech text, and voice_consent=true.

[email protected]
input=your text here
voice_consent=true

2. Production segments

For many short lines, call /api/v2/audio/clone/jobs with items. Put your segment ID in id or external_id so status payloads map back to your video segments.

items[0].id=episode01_seg_0001
items[0].text=Khmer line text
output=merged WAV + ZIP

3. Timing work

The API returns WAV audio. Your dubber should trim leading silence and fit audio to the target video timing after download.

trim leading silence
fit to start_ms/end_ms
mix into video

Live API test

Test Console

Paste a paid API key and send a real request from this browser. The key stays only in this form state and is not saved. Requests can use tokens.

Manage Keys

https://voxtts.online/api/v2/audio/clone/jobs

Async clone — returns job_id immediately, then poll for completion. No timeout.

API key

Text input

Reference audio

This console uses the production clone format: multipart/form-data with sample, input, model, voice_consent=true, and output_format=wav.

POST/api/v2/audio/jobs

Async Audio Jobs V2

Recommended for all voice cloning and long-form TTS. Submit a job, poll status, then download merged WAV. Long text is split into safe worker segments automatically. Returns job_id immediately — no timeout issues.

Standard TTS jobexample

curl -X POST "https://voxtts.online/api/v2/audio/jobs" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "input": "long script text here",
    "voice": "female",
    "model": "voxcpm2",
    "webhook_url": "https://your-app.com/tts-webhook",
    "output_format": "wav"
  }'

Standard TTS jobexample

curl -X POST "https://voxtts.online/api/v2/audio/jobs?api_key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "input": "long script text here",
    "voice": "female",
    "model": "voxcpm2",
    "webhook_url": "https://your-app.com/tts-webhook",
    "output_format": "wav"
  }'

Poll and downloadexample

curl "https://voxtts.online/api/v2/audio/jobs/JOB_ID?api_key=YOUR_API_KEY"

curl "https://voxtts.online/api/v2/audio/jobs/JOB_ID/audio?api_key=YOUR_API_KEY" \
  --output result.wav

Field	Type	Description
input	string or array	Required. Long strings are automatically split into safe worker segments.
items	JSON array	Clone endpoint also accepts items for segment metadata and external IDs.
webhook_url	string	Optional. Completion callback includes status_url, audio_url, zip_url, and per-item status.
output_format	string	Optional. The public API always returns WAV.

POST/api/v1/audio/speech

Text to Speech

Generate speech from text. Works for any text length. Returns a job ID immediately — poll for the result. No timeout issues.

cURL (recommended: query param auth)example

curl -X POST "https://voxtts.online/api/v1/audio/speech?api_key=YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "voxcpm2",
    "voice": "female",
    "input": "your text here (any length)",
    "output_format": "wav"
  }'

# Response: {"ok":true,"queued":true,"job":{"id":"..."},"poll_url":"..."}

Poll job statusexample

curl "https://voxtts.online/api/v1/audio/batch/jobs/JOB_ID?api_key=YOUR_API_KEY"

# While processing: {"job":{"status":"running","completed_items":0}}
# When done: {"job":{"status":"completed","credits_charged":3}}

Download audioexample

curl "https://voxtts.online/api/v1/audio/batch/jobs/JOB_ID/download?api_key=YOUR_API_KEY"   --output audio.zip

Pythonexample

import requests, time

BASE = "https://voxtts.online"
KEY = "YOUR_API_KEY"

# Submit job
resp = requests.post(f"{BASE}/api/v1/audio/speech?api_key={KEY}",
    json={"model":"voxcpm2","voice":"female","input":"your text here","output_format":"wav"})
job_id = resp.json()["job"]["id"]

# Poll until complete
while True:
    status = requests.get(f"{BASE}/api/v1/audio/batch/jobs/{job_id}?api_key={KEY}").json()
    if status["job"]["status"] in ("completed","partial","failed"):
        break
    time.sleep(2)

# Download audio
audio = requests.get(f"{BASE}/api/v1/audio/batch/jobs/{job_id}/download?api_key={KEY}")
open("audio.zip", "wb").write(audio.content)
print(f"Credits charged: {status['job']['credits_charged']}")

Field	Type	Description
input	string	Required. 1 to 5,000 characters. Any length works — long text is split automatically.
voice	string	Optional. 'female' (Sokha) or 'male' (Piseth).
model	string	Optional. Default is voxcpm2.
output_format	string	Optional. The public API always returns WAV.

Tokens and limits

Token Deductions

Standard Speech1.5 tokens / generated audio sec
Standard Voice Cloning2.0 tokens / generated audio sec
Approved Business Clone1.5 tokens / generated audio sec

Platform Safety Default Limits

Max Input Characters5,000 chars
Max Reference Audio size8 MB
API Concurrent Requests4 concurrency

Response Metadata

Job submission endpoints (speech, batch, clone jobs) return a JSON job envelope with HTTP 202 — including the job id, poll_url, and audio_url — never audio bytes. Audio downloads are WAV (PCM-16, mono, 24 kHz) with Content-Type: audio/wav. Usage metadata is available in the job status JSON (credits_charged, output_seconds) and in the download response headers below.

Content-Type

audio/wav (download endpoints only)

X-Remaining-Tokens

Available prepaid token balance left on the user's account after deducting for this request.

X-Credits-Charged

Prepaid tokens deducted for the generation duration.

X-Generation-Duration-Seconds

The exact duration of the generated audio in seconds (used to calculate X-Credits-Charged).

Failure states

Errors

HTTP Code	Cause / Recovery
401	Missing bearer token.
403	Invalid bearer token or suspended account.
402	Insufficient tokens for this request.
429	Rate limit or concurrency limit reached.
502	Upstream TTS worker failed.

Payment readiness

Payment Webhooks

Current checkout uses KHQRcc ABA Pay QR. Configure the callback URL below in KHQRcc so the app can check signature, amount, currency, order status, and duplicate callbacks before adding credits automatically.

Webhook URLexample

https://voxtts.online/api/webhooks/khqrcc

Current mode

KHQRcc ABA Pay QR checkout

Verification

Signed callback + transaction check

Payment Guide Refund Policy

curl -X POST "https://voxtts.online/api/v2/audio/jobs" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ --data '{ "input": "long script text here", "voice": "female", "model": "voxcpm2", "webhook_url": "https://your-app.com/tts-webhook", "output_format": "wav" }'

curl -X POST "https://voxtts.online/api/v2/audio/jobs?api_key=YOUR_API_KEY" \ -H "Content-Type: application/json" \ --data '{ "input": "long script text here", "voice": "female", "model": "voxcpm2", "webhook_url": "https://your-app.com/tts-webhook", "output_format": "wav" }'

Field

Type

Description

input

string or array

Required. Long strings are automatically split into safe worker segments.

items

JSON array

Clone endpoint also accepts items for segment metadata and external IDs.

webhook_url

string

Optional. Completion callback includes status_url, audio_url, zip_url, and per-item status.

output_format

string

Optional. The public API always returns WAV.

curl -X POST "https://voxtts.online/api/v1/audio/speech?api_key=YOUR_API_KEY" -H "Content-Type: application/json" -d '{ "model": "voxcpm2", "voice": "female", "input": "your text here (any length)", "output_format": "wav" }' # Response: {"ok":true,"queued":true,"job":{"id":"..."},"poll_url":"..."}

curl "https://voxtts.online/api/v1/audio/batch/jobs/JOB_ID?api_key=YOUR_API_KEY" # While processing: {"job":{"status":"running","completed_items":0}} # When done: {"job":{"status":"completed","credits_charged":3}}

import requests, time BASE = "https://voxtts.online" KEY = "YOUR_API_KEY" # Submit job resp = requests.post(f"{BASE}/api/v1/audio/speech?api_key={KEY}", json={"model":"voxcpm2","voice":"female","input":"your text here","output_format":"wav"}) job_id = resp.json()["job"]["id"] # Poll until complete while True: status = requests.get(f"{BASE}/api/v1/audio/batch/jobs/{job_id}?api_key={KEY}").json() if status["job"]["status"] in ("completed","partial","failed"): break time.sleep(2) # Download audio audio = requests.get(f"{BASE}/api/v1/audio/batch/jobs/{job_id}/download?api_key={KEY}") open("audio.zip", "wb").write(audio.content) print(f"Credits charged: {status['job']['credits_charged']}")

Field

Type

Description

input

string

Required. 1 to 5,000 characters. Any length works — long text is split automatically.

voice

string

Optional. 'female' (Sokha) or 'male' (Piseth).

model

string

Optional. Default is voxcpm2.

output_format

string

Optional. The public API always returns WAV.

Response Metadata

Content-Type

audio/wav (download endpoints only)

X-Remaining-Tokens

Available prepaid token balance left on the user's account after deducting for this request.

X-Credits-Charged

Prepaid tokens deducted for the generation duration.

X-Generation-Duration-Seconds

The exact duration of the generated audio in seconds (used to calculate X-Credits-Charged).

HTTP Code

Cause / Recovery

401

Missing bearer token.

403

Invalid bearer token or suspended account.

402

Insufficient tokens for this request.

429

Rate limit or concurrency limit reached.

502

Upstream TTS worker failed.

Payment Webhooks

Webhook URLexample

https://voxtts.online/api/webhooks/khqrcc

Current mode

KHQRcc ABA Pay QR checkout

Verification

Signed callback + transaction check

Developer Docs

infoOverview

Text to Speech

Batch TTS

Clone Voice

Quickstart

Use this setup for video dubbing tools

1. First live test

2. Production segments

3. Timing work

Test Console

Async Audio Jobs V2

Text to Speech

Tokens and limits

Token Deductions

Platform Safety Default Limits

Response Metadata

Errors

Payment Webhooks

Calibrating Vocal Cords...

Developer Docs

infoOverview

Text to Speech

Batch TTS

Clone Voice

Quickstart

Use this setup for video dubbing tools

1. First live test

2. Production segments

3. Timing work

Test Console

Async Audio Jobs V2

Text to Speech

Tokens and limits

Token Deductions

Platform Safety Default Limits

Response Metadata

Errors

Payment Webhooks

Overview

Overview