Open Source Models

SLNG. is committed to supporting the open source community by providing easy access to leading open source speech models. Below you'll find the models currently available on our platform, with links to their API documentation for quick integration.

Available Open Source Models

Whisper (OpenAI)

• Description: State-of-the-art automatic speech recognition (ASR) model supporting dozens of languages. Ideal for transcription, captioning, and voice command applications.
• API Reference: Whisper STT API

XTTS-v2 (coqui.ai)

• Description: High-quality multilingual text-to-speech (TTS) model with voice cloning capabilities. Great for generating natural-sounding speech in many languages and accents.
• API Reference: XTTS-v2 TTS API

Mars6 (CAMB.AI)

• Description: Advanced TTS model with support for voice/prosody cloning and multiple languages. Designed for expressive, high-fidelity speech synthesis.
• API Reference: Mars6 TTS API

Orpheus

• Description: Open source TTS model focused on natural prosody and clarity, suitable for a wide range of voice applications.
• API Reference: Orpheus TTS API

VUI

• Description: Versatile, open source TTS model designed for fast, high-quality speech generation in multiple languages.
• API Reference: VUI TTS API

Twi SpeechT5

• Description: Specialized TTS model for the Twi language, supporting speaker embedding for voice customization.
• API Reference: Twi SpeechT5 TTS API

We're always adding new open source models! If you'd like to see a specific model supported, let us know.