Text-to-speech (TTS) technology in 2026 has reached a level where synthesized voices can closely mimic human speech in both accuracy and expressiveness. Trelis Research examines this progress by ...

Gradium Phonon is a 31M-parameter on-device TTS model under Apache 2.0, reporting 1.70% WER on hard English sentences.

The enterprise voice AI market is in the middle of a land grab. ElevenLabs and IBM announced a collaboration just this week to bring premium voice capabilities into IBM's watsonx Orchestrate platform.

Qwen TTS, Alibaba’s open source text-to-speech model, offers new options for voice synthesis by allowing users to adjust tone and emotion through natural language commands instead of traditional ...

A Chinese startup called Yunshang Qulv released an open-source text-to-speech model on July 1, 2026, that does something no commercially deployed rival currently offers: it replaces a single word ...

The Paris-based Mistral AI SAS today announced the release of Voxtral TTS, its first text-to-speech artificial intelligence model aimed at unseating the best-known and most powerful voice models on ...

This week, Fish Audio released Fish Audio Drama 3. Drama 3 is a text-to-speech model from Fish Audio that takes ...

Xiaomi has announced that its AI Lab’s new-generation Kaldi team has open-sourced a new text-to-speech (TTS) model called OmniVoice. According to the company, the model is designed to deliver ...