YupVox Logo
YupVox
REST API v1.0 • 48kHz Studio Quality • 3,000+ Voices

High-Performance AI Voice & Audio API for Developers

Integrate ultra-natural Text-to-Speech (TTS), Instant Voice Cloning, Speech-to-Text (STT), Subtitle SRT sync, and AI Dubbing into your applications with just a few lines of code.

Try Live Code Snippets
< 800ms
Sub-second Latency
3.000+
Studio-Grade Voices
600+
Global Languages & Accents
99.9%
GPU Cluster Uptime SLA
Live Code Playground & EndpointsREST v1.0

Select a capability and language to view production-ready request and response payloads.

POST/v1/tts

Synthesize speech from text using 3,000+ studio-grade 48kHz voices with Natural, Narration, or Dramatic style presets.

curl -X POST "https://api.yupvox.com/v1/tts" \
  -H "Authorization: Bearer sk-yupvox-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voiceId": "DFE237",
    "text": "Hello, this is a high-quality AI voice generated by the YupVox API.",
    "speed": 1.0,
    "pitch": 0
  }'
HTTP 200 OK (Response JSON)
application/json
{
  "success": true,
  "data": {
    "jobId": "tts_82910_1725184900000",
    "historyId": 82910,
    "status": "processing",
    "voiceId": "DFE237",
    "charCount": 62,
    "estimatedTimeSec": 1.2
  }
}
Need complete specifications for all 10 endpoints, pagination parameters, and SDK guides?
View API Docs
Full-Stack Audio Intelligence

6 Core Capabilities of YupVox API

All cutting-edge voice and audio AI algorithms unified under a single, robust REST API.

Text to Speech

Ultra-Natural 48kHz TTS

3,000+ studio voices with natural pacing, audiobooks narration, and emotional drama styles.

Dual Engine

Instant Voice Cloning API

Instant zero-shot voice cloning. Dual-engine architecture with Omega (multilingual) & Alpha (ultra-fast VN).

Speech to Text

Precision Speech to Text

High-accuracy automatic speech recognition with timestamps, punctuation, and multi-speaker support.

Subtitle Sync

Subtitle-to-Audio (SRT)

Convert SRT subtitle text into perfectly timed audio segments aligned with original video frames.

Voice Changer

AI Voice Changer

Transform speaker timbre and tone into target AI voices while retaining nuance and cadence.

Dubbing Video

Video & Audio Dubbing

End-to-end automated pipeline: Transcribe → Translate → Synthesize localized voice audio.

Seamless Integration in 3 Steps

Start generating high-quality speech in under 3 minutes.

01

Generate Your API Key

Sign up for free and get your secret API key (`sk-yupvox-...`) with 50,000 complimentary credits.

02

Send REST HTTP Request

Call standard REST endpoints using any language (cURL, Python, Node.js, Go) with Bearer token authentication.

03

Receive Studio-Quality Audio

Instantly download high-bitrate MP3/WAV audio via high-speed CDN ready for streaming or download.

Empowering Real-World Applications

Trusted by creators, SaaS platforms, media publishers, and conversational AI developers.

Short Video Automation (TikTok / Shorts)

Generate thousands of daily automated videos with captivating, viral-ready AI voiceovers.

AI Voice Bots & Conversational IVR

Sub-second latency enabling natural conversational AI agents, smart IVR, and customer support bots.

Audiobooks & Automated News Reader

Convert entire article repositories and e-books into studio-grade audiobooks with narrative pacing.

EdTech & Course Localization

Automatically dub educational courses into dozens of global languages for international students.

Transparent Pricing • No Hidden Cost

1 Credit = 1 Character • Shared Across All Tools

Your credit balance is shared seamlessly between the web studio and API calls. No setup fees, no per-request surcharge.

View Pricing Plans

Developer FAQs

How is YupVox API billed?

Simple 1:1 transparent ratio: 1 Credit = 1 Character generated (TTS) or transcribed (STT). API requests draw from your account credit balance with no hidden API fees.

Is there a concurrency limit on API requests?

YupVox GPU cloud infrastructure uses distributed worker queues, allowing high concurrent requests without artificial bottlenecks.

What is the typical response latency for TTS?

Demo preview mode responds in 0.5s - 1.5s. Full production conversions process via asynchronous background queues within a few seconds depending on text length.

Can I test the API before purchasing a paid plan?

Yes! Upon creating an account, you receive 50,000 free trial credits to test all voice models and studio tools.

Is my text and audio data secure?

100% data security. Cloned voice models are strictly encrypted and tied to your account ID. You can also permanently delete history records and files via API.

Ready to Supercharge Your App with Voice AI?

Create your account today to receive 50,000 free credits and integrate studio-grade AI voices into your pipeline.

Contact Enterprise Support