Text-to-Speech

Overview

Text-to-speech (TTS) models convert written text into natural-sounding speech, enabling a wide range of applications, from voice assistants and audiobooks to accessibility tools for visually impaired users. These models use deep learning techniques, such as neural vocoders and transformer-based architectures, to generate human-like speech with variations in tone, pitch, and emphasis. Many modern TTS systems support multiple languages, voices, and even emotional expressions for more engaging and realistic audio output.

Advanced TTS models offer features like speaker adaptation, voice cloning, and fine-tuned prosody control, allowing for highly customizable speech synthesis. Some solutions run on-device for real-time applications, while cloud-based TTS services provide scalable, high-quality synthesis for larger workloads. Developers can integrate TTS into their applications through APIs, enabling dynamic voice generation for customer support, content creation, and assistive technologies.

All Available Text-to-Speech Models

Model ID	Developer	Context	Model Card
#g1_aura-angus-en	Deepgram		Aura
#g1_aura-arcas-en	Deepgram		Aura
#g1_aura-asteria-en	Deepgram		Aura
#g1_aura-athena-en	Deepgram		Aura
#g1_aura-helios-en	Deepgram		Aura
#g1_aura-hera-en	Deepgram		Aura
#g1_aura-luna-en	Deepgram		Aura
#g1_aura-orion-en	Deepgram		Aura
#g1_aura-orpheus-en	Deepgram		Aura
#g1_aura-perseus-en	Deepgram		Aura
#g1_aura-stella-en	Deepgram		Aura
#g1_aura-zeus-en	Deepgram		Aura