Recent advancements in text-to-speech (TTS) technology have been highlighted by the introduction of two innovative models: Kokoro and Hailuo's T2A-01-HD. Kokoro, a TTS model with only 82 million parameters, has been noted for its ability to outperform larger models, generating minutes of speech in seconds. It is licensed under APACHE 2.0 and was trained on less than 100 hours of audio. Meanwhile, Hailuo's T2A-01-HD model is being recognized as the industry's first emotionally intelligent system, capable of replicating subtle emotions in speech, marking a significant step forward in voice synthesis capabilities.