Models

View as Markdown

Text to Speech (TTS) Models

Lightning v2 is deprecated. New integrations should use Lightning v3.1. The v2 endpoints remain available for existing callers but are not recommended for new work.

Speech to Text (STT) Models

Click on a model name to view its detailed model card.

Geo-location Based Routing

Waves intelligently routes every request to the nearest server cluster to ensure the lowest possible latency for your applications. We currently operate server clusters in:

  • India (Mumbai)
  • USA (Oregon)

Our routing system automatically detects the client’s geographical location and connects them to the optimal server based on network proximity and latency. This process is fully automated, no manual configuration is required on your side.

Model Overview (TTS)

Model IDDescriptionLanguages Supported
lightning-v3.1 Latest44 kHz model, natural expressive speech, ultra-low latency, supports voice cloning.English
Hindi
Marathi
Kannada
Tamil
Bengali
Gujarati
Telugu
Malayalam
Punjabi
Odia
Spanish
auto

Model Overview (STT)

Model IDDescriptionLanguages Supported
pulseLow-latency speech-to-text model supporting automatic language detection and real-time transcription.Italian
Spanish
English
Portuguese
Hindi
German
French
Ukrainian
Russian
Kannada
Malayalam
Polish
Marathi
Gujarati
Czech
Slovak
Telugu
Oriya (Odia)
Dutch
Bengali
Latvian
Estonian
Romanian
Punjabi
Finnish
Swedish
Bulgarian
Tamil
Hungarian
Danish
Lithuanian
Maltese
Japanese
Korean
Chinese
Malay
Indonesian
Tagalog

Note: The API uses ISO 639-1 language codes - Set 1 (2-letter codes) to specify supported languages.

Pricing

Our pricing model is designed to be flexible and scalable, catering to different usage needs. For detailed pricing information, please visit our pricing page or contact our sales team at support@smallest.ai.