This repo is a minimalist and extensible framework for benchmarking various aspects of different text-to-speech (TTS) engines. This benchmark simulates user - voice-assistant interactions, by ...

Here is a short tutorial. I don't know what to call it, call it funny text even though it doesn't look very funny Thanks for watching Republicans react to Donald Trump's Iran war speech Dietitians say ...

French AI company Mistral released a new open source text-to-speech model on Thursday that can be used by voice AI assistants or in enterprise use cases like customer support. The model, which lets ...

This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time.

WhisperS2T is an optimized lightning-fast open-sourced Speech-to-Text (ASR) pipeline. It is tailored for the whisper model to provide faster whisper transcription. It's designed to be exceptionally ...

Abstract: Speech synthesis, the technology that converts text into spoken words, has advanced significantly for high-resource languages like English, Spanish, and Mandarin. However, many languages ...

Abstract: While waveform-domain speech enhancement (SE) has been extensively investigated in recent years and achieves state-of-the-art performance in many datasets, spectrogram-based SE tends to show ...

AssemblyAI builds advanced speech language models that power next-generation voice AI applications. AssemblyAI builds advanced speech language models that power next-generation voice AI applications.