Text to Speech (TTS) Models
Lightning v2
An upgrade from the Lightning Large model, offering improved performance and
quality. It supports 16 languages, making it suitable for a wider range of
applications requiring expressive and high-quality speech synthesis.
Lightning v3.1
A 44 kHz model delivering natural, expressive, and realistic speech. Supports voice cloning with ultra-low latency. Supports English, Hindi, Tamil, and Spanish.
Speech to Text (STT) Models
Pulse STT
High-accuracy, low-latency automatic speech recognition model built for
real-time transcription. It supports automatic language detection across 32
languages and delivers fast, reliable results.
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)
Model Overview (TTS)
| Model ID | Description | Languages Supported |
|---|---|---|
| lightning-v2 | 100ms TTFB, Supports 16 languages with voice cloning. | English Hindi Tamil Kannada Malayalam Telugu Gujarati Bengali Marathi German French Spanish Italian Polish Dutch Russian Arabic Hebrew Swedish |
| lightning-v3.1 | 44 kHz model, natural expressive speech, ultra-low latency, supports voice cloning. | English Hindi Tamil Spanish |
Model Overview (STT)
| Model ID | Description | Languages Supported |
|---|---|---|
| pulse | Low-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 |
Note: The API uses ISO 639-1 language codes - Set
1 (2-letter
codes) to specify supported languages.