Skip to main content

Supported Languages

Kallglot supports real-time voice translation across 29 languages. Kallglot abstracts:
  • Speech-to-Text (STT)
  • Real-time translation
  • Text-to-Speech (TTS)
into a single real-time API. No additional configuration is required.

What “Supported” Means

All supported languages include:
  • Speech-to-Text (STT)
  • Real-time translation
  • Text-to-Speech (TTS)
All languages support bidirectional voice conversations. Latency may vary depending on language.

Latency Overview

Latency may vary slightly depending on network conditions and call routing.

Real-Time Languages

These languages are optimized for low-latency conversations (~1–1.5s).

Extended Languages

These languages are fully supported but may have higher latency (~3–4s).

Regional Variants

For improved transcription accuracy, you can specify regional variants using ISO language and country codes.

Using Regional Variants

Kallglot automatically applies the appropriate models.

Language Detection

Kallglot can automatically detect the spoken language:

Notes

  • Initial detection may take 2–3 seconds
  • Works best when speakers use a single language
  • Accuracy improves with more audio

Detected Language Event

When using auto-detection, you’ll receive a language_detected event via WebSocket:

Translation Quality

Highest Quality

  • English ↔ German
  • English ↔ French
  • English ↔ Spanish
  • English ↔ Italian
  • English ↔ Portuguese
  • English ↔ Dutch
  • English ↔ Japanese
  • English ↔ Chinese
  • German ↔ French
  • Spanish ↔ Portuguese

High Quality

All combinations between:
  • English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian

Standard

All other supported combinations are handled automatically.

Voice Options

Custom Voices (Kallglot Managed)

Kallglot supports custom voice deployment for enterprise and B2B use cases. This allows you to:
  • Use a branded voice
  • Maintain a consistent voice across calls
  • Deploy voice identity across languages
Available as part of Kallglot-managed deployments.

Standard Voices

Kallglot uses high-quality neural voices optimized for:
  • Low latency
  • Clarity in phone calls
  • Natural conversational tone
Voice selection is handled automatically or can be configured via the API.

Using a Voice

If no voice is provided, Kallglot selects one automatically.

Best Practices

When you know the language, always specify it rather than using auto-detection. This improves accuracy and reduces latency.
For Swiss customers, use de-CH, fr-CH, or it-CH for better recognition of regional accents and vocabulary.
Test your specific language pair before going live. Some pairs may need fine-tuning for domain-specific terminology.
For specialized vocabulary (medical, legal, technical), create custom glossaries to ensure consistent translation.

Expanding Language Support

Kallglot is continuously expanding language coverage. If you need a specific language or voice capability, contact us at support@kallglot.com.