Dia is a 1.6 billion parameter text-to-speech model developed by Nari Labs, capable of generating highly realistic dialogues directly from text, supporting emotional and intonation adjustments as well as non-verbal expression generation.

Orpheus is a Turkish text-to-speech (TTS) model based on canopylabs/orpheus-3b-0.1-pretrained, supporting multiple emotional expressions.

Audio ProcessingSafetensorsOther

A German text-to-speech (TTS) model based on Orpheus-3B, supporting multiple speakers and emotional expression.

Audio ProcessingTransformersMultiple Languages

A VITS-based text-to-speech model supporting 13 Indian languages with diverse speaking styles and emotional expressions

Audio ProcessingTransformersOther

HelpingAI-TTS-v1 is a top-tier text-to-speech model that focuses on personalization, emotional expression, and clear delivery. It can intelligently adjust tone, speed, and style according to the text content, generating high-quality, natural, and fluent voice output.

Audio ProcessingTransformersMultiple Languages

HelpingAI-TTS-v1 is a next-generation text-to-speech (TTS) tool focused on personalization, emotional expression, and clarity, supporting multiple languages and emotion customization.

Audio ProcessingTransformersMultiple Languages

A Chinese text emotion intensity detection model fine-tuned based on BERT architecture, capable of distinguishing between weak and strong emotional expressions

Natural Language ProcessingTransformersChinese

A multilingual text-to-speech model fine-tuned with C-3PO's voice from Star Wars, featuring sarcastic tone and emotional expression

A fully remastered 32k context large language model based on TeeZee/DarkSapling-7B-v1.1, excelling in instruction following, reasoning depth, and emotional expression

Natural Language ProcessingGgufEnglish

A merged model optimized for role-playing with high sensitivity and intelligent performance, particularly adept at capturing subtle settings and emotional expressions.

Natural Language ProcessingTransformersEnglish