Frequently Asked Questions

Everything you need to know about Pekci.

Can't find what you're looking for? Contact our support team.

Calder Latency: ~120ms
"Welcome to Pekci. Experience human-like speech generated in real-time with precise emotional control and zero perceptible lag."
Calder Energetic
Aspen Professional
Willow Friendly

Calder Voice Node

Calder is optimized for action-packed and energetic environments. He maintains high emotional range and fast responses suitable for interactive gaming and agentic roles.

realtime_stream.log 
[10:14:02.102] CONNECTING TO PEKCI REALTIME ENDPOINT...
[10:14:02.215] INSTANCE CREATED: VOICE_MODEL_ID = "calder-v3"
[10:14:02.220] DUPLEX_STREAM_OPENED
[10:14:02.230] LATENCY: 98ms | SAMPLE_RATE: 24kHz
[10:14:02.250] READY TO TRANSCRIBE / SYNTHESIZE
Click mic to start speaking
transcription_stream.json
// Transcribed text will appear here in real-time...

Router Matching Rules

{
  "route": "/*",
  "rules": [
    {
      "condition": "query.intent == 'chat'",
      "model": "pekci-lite-v4",
      "fallback": "gpt-4o-mini"
    }
  ]
}

Live Test Response

Hi, can you tell me a short joke?

Why did the AI go to therapy? It had too many bugs in its system! 😄

via pekci-lite-v4 (95ms)

Voice AI that fits your exact use case

1M+ Users registered in 19 days
98.5% User retention score

AI Companions & NPCs

Bring your virtual characters, NPCs, and AI companions to life with realistic, full-duplex conversational audio. Supports deep emotional states, personality styles, and contextual awareness.

Explore AI Companions
PRICING PLANS

Pricing that scales with you

Save up to 90% on TTS costs compared to industry competitors. Subscribe monthly or yearly for additional volume discounts and premium features.

Special offer Subscribe to a monthly plan by June 30 and get double the credits for your first month.

On-Demand

Evaluation and prototyping
Start free
TTS-2 $1.50/1M chars
STT 1 $0.10/hr
LLMs At cost
Choose On-Demand
  • Up to 70 min TTS included
  • 100 custom voices
  • Voice cloning & voice design
  • Realtime API access
  • 220+ LLM models via Router
  • Commercial license
  • Community support

Creator

Content creation and small projects
$25/mo
TTS-2 $1.50 $1.15$1.00/1M chars
STT 1 $0.10 $0.07/hr
LLMs At cost
Choose Creator
  • $25 in credits per month
  • Up to 33% off TTS & STT rates
  • 500 custom voices
  • Audio downloads
  • 40K chars per TTS Playground request
  • Workspace creation & sharing
  • + Everything in On-Demand
Popular

Builder

Growing projects and small teams
$100/mo
TTS-2 $1.50 $1.05$0.90/1M chars
STT 1 $0.10 $0.07/hr
LLMs At cost
Choose Builder
  • $100 in credits per month
  • Up to 40% off TTS & STT rates
  • 3,000 custom voices
  • Increased concurrency limits
  • Workspace creation & sharing
  • Team management
  • + Everything in Creator

Developer

Production applications
$300/mo
TTS-2 $1.50 $0.90$0.75/1M chars
STT 1 $0.10 $0.06/hr
LLMs At cost
Choose Developer
  • $300 in credits per month
  • Up to 50% off TTS & STT rates
  • 10,000 custom voices
  • Increased concurrency limits
  • Professional voice cloning (add-on)
  • Priority email support
  • + Everything in Builder

Growth

Large deployments & compliance
$1,500/mo
TTS-2 $1.50 $0.75$0.60/1M chars
STT 1 $0.10 $0.05/hr
LLMs At cost
Choose Growth
  • $1,500 in credits per month
  • Up to 60% off TTS & STT rates
  • 30,000 custom voices
  • Higher API concurrency & limits
  • 1 professional voice clone
  • ZDR, HIPAA & BAA (add-ons)
  • + Everything in Developer

Enterprise

Custom pricing, limits & terms
Custom
TTS-2 As low as $0.25/1M
STT 1 Custom
LLMs Custom
contact sales
  • Price match available
  • Custom limits
  • SLA & DPA
  • On-prem deployment
  • EU & India data residency
  • Dedicated AM & Slack channel
  • + Everything in Growth
REALTIME TTS

Ultra-fast, customizable, high-fidelity synthesis

Our state-of-the-art TTS engine transforms text into high-fidelity lifelike vocal audio with minimal latency, supporting dynamic emotion control and custom voice design features.

Vocal Quality Benchmark (Human ELO Score)

Pekci Voice Engine
4.82
ElevenLabs v2
4.78
Cartesia Sonic
4.45
OpenAI TTS
4.40
✨

#1 Realtime TTS Quality

Natural intonation, lifelike breathing patterns, and high-fidelity 24kHz output.

🎙️

Advanced Voice Direction

Inject inline SSML tags to adjust speaking speed, pitch, emotion, and pauses dynamically.

👥

Instant Voice Cloning

Clone any voice using a short 10-second reference audio file with high accuracy.

🌍

Over 100 Languages

Global support for localized accents, dialects, and multi-lingual voice matching.

🎨

Text-based Voice Design

Create completely custom voices simply by writing a text description of the persona.

⚡

Realtime Latency

First-byte latency under 120ms, perfectly suited for interactive streaming.

Voice AI that feels human, across every industry

"Pekci's TTS changed the way we build NPCs. The speed and quality are unprecedented. Our players now feel like they are talking to real people."
LK
David Zhao Co-Founder, LiveKit
"We slashed our monthly server costs by 70% when migrating our voice avatars to Pekci. We were shocked by how good the voice quality remained."
LV
Sarah Chen Head of Product, Luvu
"Having real-time low-latency voice responses is critical for language learners. Talkpal users can now converse fluently with zero awkward pauses."
TP
Alex G. CTO, Talkpal
"The developer API is straightforward and the billing transparent. We integrated Pekci STT and TTS in less than two days."
AI
Eliza Vance Lead AI Architect, Synthesia
REALTIME API

The fully integrated conversation layer

Everything you need to orchestrate voice-to-voice agents: STT, LLM orchestration, turn-taking, and TTS in a unified stream.

Session Active • Audio Stream 00:14.32
User

"What's the forecast for the launch tomorrow?"

AI Agent (Calder)

"Looking good! Winds are under 10 knots, skies are clear, and we are go for launch."

Emotion: Excited VAD: Silent Latency: 92ms

Full Duplex Streaming

Simultaneous bidirectional audio streaming so users can interrupt the agent naturally.

Turn Taking & VAD

Advanced voice activity detection checks whether a user has finished speaking or just paused.

Tool & Function Calling

Trigger database queries or external API events directly during the voice conversation.

Emotion Modulation

AI vocal intonation automatically updates based on the sentiment of the conversation.

Context Persistence

Maintains state, memory, and past history of the dialogue across multiple active sessions.

Custom System Prompts

Inject goals, knowledge bases, and behaviors to style the agent's logic flow.

REALTIME ROUTER

Optimize for cost, latency, and capability

The Pekci Router intercepts conversational intents and dynamically assigns them to the best-fit model (e.g. OpenAI GPT, Anthropic Claude, Meta Llama, or Pekci Lite) based on the target task.

Router Traffic Allocation

Pekci Lite-v4
58%
GPT-4o / Claude 3.5
27%
Llama 3 (Local)
15% 
{
  "router": "user-aware-v1",
  "strategies": {
    "free_tier": "pekci-lite-v4",
    "premium_tier": "gpt-4o-realtime",
    "latency_sensitive": "pekci-direct-tts"
  }
}
"The waterfall cascading down..."
"High precision audio capture"
REALTIME STT

State-of-the-Art Speech-to-Text

Our speech-to-text models are optimized for conversational speech, featuring rapid word alignment, semantic punctuation, and background noise cancellation.

Voice Profiling

Differentiate between background noise, speaker crosstalk, and targeted audio input.

Semantic VAD

Detect natural breathing and conversational pause intervals with high precision.

Word-Level Timestamps

Align every transcribed word with millisecond accuracy for closed-captioning feeds.

ENTERPRISE SECURITY

Enterprise-grade security and compliance

We take safety and data privacy seriously. Our architecture complies with key security frameworks, ensuring your users' data remains isolated, encrypted, and compliant.

  • • End-to-end data encryption in transit and at rest.
  • • Zero retention option for sensitive interactions.
  • • Standard VPC deployment and dedicated tenant hosting.
SOC2 TYPE II
HIPAA
GDPR COMPLIANT
CAPABILITY MATRIX

How Pekci compares with legacy models

Get advanced conversation logic and low latency at a fraction of the cost.

Feature Pekci Voice Engine ElevenLabs Cartesia OpenAI Google Cloud
Sub-150ms Latency ✓ (Under 120ms) ✓ ✓ – ✓
Voice Design (Text-to-Voice) ✓ – – – –
Inline SSML Tag Control ✓ – ✓ – ✓
User-Aware LLM Routing ✓ – – – –
Cost per 1M characters $1.50 $15.00 $10.00 $15.00 $4.00

Ready to build the future of voice interactions?

Get started with 1 Million free characters. No credit card required. Deploy in minutes.

GET STARTED FREE TALK TO AN EXPERT