Routing

Regions

Overview

slng.ai operates infrastructure across multiple global regions to provide low-latency, compliant AI model serving for our SLNG.ai models. Each region offers specific models and ensures data residency within your chosen geographic boundaries.

Note: This page covers regional availability for SLNG.ai models only. Proprietary models (ElevenLabs, OpenAI Whisper, etc.) have separate regional availability and are documented separately.

Our global infrastructure supports both standard regions with comprehensive SLNG.ai model availability and premium regions for specialized use cases. All regions maintain the same security standards and API compatibility.

---

🌍 Standard Region Availability

Region	Country	Subregion	Region Name	Description
North America	USA	US-East	us-east-1	AWS Virginia
North America	USA	US-West	us-west-1	AWS California
Europe	Germany	EU-West	eu-central-1	AWS Frankfurt
Europe	France	EU-West	eu-west-3	AWS Paris
Europe	Netherlands	EU-West	europe-west4	GCP Netherlands
Europe	Ireland	EU-West	eu-west-1	AWS Ireland
Asia-Pacific	India	AP-South	ap-south-1	AWS Mumbai
Asia-Pacific	Singapore	AP-Southeast	asia-southeast1	GCP Singapore

---

💎 Premium Regions

Region	Country	Subregion	Region Name	Description
North America	Canada	CA	ca-central-1	AWS Montreal
Europe	UK	UK	eu-west-2	AWS London
Latam	Brazil	SA	sa-east-1	AWS São Paulo
Middle East	Israel	ME-West	me-west1	GCP Tel Aviv

---

Region Selection

Standard vs Premium

• Standard Regions: Full model availability, optimized pricing, and guaranteed capacity
• Premium Regions: Specialized infrastructure for specific compliance or latency requirements, contact us for access.

Geographic Distribution

Our regions are strategically distributed across:

• North America: 3 regions (US East & West, Canada)
• Europe: 5 regions (Germany, United Kingdom, France, Netherlands, Ireland)
• Asia-Pacific: 2 regions (India, Singapore)
• Middle East: 1 region (Israel)
• Latin America: 1 region (Brazil)

---

Using Regions in API Calls

Basic Region Selection

Code
 
POST /tts
Content-Type: application/json

{
  "text": "Process this in Europe",
  "language": "en-GB",
  "region": "eu-central-1"
}

cURL Example

Code
 
curl -X POST https://api.slng.ai/tts \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Process this in Europe",
    "language": "en-GB",
    "region": "eu-central-1"
  }'

---

Regional Features

Data Residency

• Guaranteed: Your data stays within the selected region
• Compliance: Supports GDPR, HIPAA, and other regional regulations
• Audit Trail: Complete logging of data processing location

Latency Optimization

• Local Processing: Minimize round-trip time for regional users
• Edge Computing: Optimized routing for real-time applications
• Performance Monitoring: Track latency metrics per region

SLNG.ai Model Availability

• Core SLNG.ai Models: Available in all standard regions
• Specialized SLNG.ai Models: May have regional restrictions
• Capacity Planning: Guaranteed availability in standard regions
• Proprietary Models: Regional availability varies by provider

---

Best Practices

Region Selection

• Choose standard regions for general use cases and cost optimization
• Use premium regions only when specific compliance or latency requirements demand it
• Consider user geography when selecting regions for optimal performance

Compliance

• Set org-level default regions for consistent data residency
• Use request-level overrides for specific compliance requirements
• Monitor fallback events to ensure no data leaves intended regions

Performance

• Test latency across regions for your specific use case
• Monitor capacity in premium regions during peak usage
• Plan fallbacks for regions with limited model availability

---

Limitations

Regional Restrictions for SLNG.ai Models

• Some specialized SLNG.ai models may only be available in specific regions
• Premium regions may have limited capacity during peak usage
• Voice cloning features may be restricted in certain jurisdictions
• Proprietary models have their own regional availability policies

Capacity Considerations

• Standard regions offer guaranteed capacity and SLAs
• Premium regions may have variable availability based on demand
• Regional maintenance windows are scheduled with advance notice

---

🎯 SLNG.ai Models vs Proprietary Models

SLNG.ai Models (Covered on this page)

These models are hosted on our infrastructure and follow our regional availability:

• TTS: VUI, Orpheus, Orpheus Indic, Kokoro, XTTS-V2, MARS6, Twi SpeechT5
• STT: Whisper V3, Whisper V3 Turbo, Whisper V3 Large Streaming, WhisperX, Kyutai
• LLM: Llama 4 Scout, Kimi K2

Proprietary Models (Separate documentation)

These models have their own regional policies and infrastructure:

• ElevenLabs Models: Regional availability varies by model tier
• OpenAI Whisper: Hosted on OpenAI infrastructure
• Other Third-party Models: Check individual provider documentation

For proprietary model regional availability, refer to:

• ElevenLabs Models
• OpenAI Whisper
• Individual provider documentation

---

Quick Links

• Get API Key
• SLNG.ai Models
• Regional Routing
• Regional Lock
• Smart Routing
• Proprietary Models
• Compliance Statement
• Pricing by Region

---

Last updated: June 2025