AI Briefing#text-to-speech
The latest AI and developer news about #text-to-speech, with the original source and a short summary.
The latest AI and developer news about #text-to-speech, with the original source and a short summary.
ElevenLabs has unveiled an advanced AI voice synthesis technology that understands the context and emotion of text well enough to reproduce even laughter.
LoRA, CFG, and chain-of-thought reduced accent leakage, hallucination, and truncation in LLM-based TTS.
Mistral unveiled the 4B Voxtral TTS, emphasizing high-quality voice in 9 languages and low latency.
Qwen3-TTS has been released with a 1.7B and 0.6B lineup, supporting voice design, voice cloning, and streaming generation.
Qwen3-TTS now supports natural language voice design and 3-second voice cloning.
Qwen3-TTS-Flash now supports 49 voices, 10 languages, and 9 dialects.
SK Planet unpacked the structure of personalized voice generation using Zero-Shot Voice Conversion.
Qwen-TTS now supports 3 Chinese dialects and Chinese-English bilingual speech.
SK Planet shared the development experience and optimization strategies behind 'AI Moment,' a B2B service that automatically generates corporate advertising videos using GPT-4o and Google TTS.
OpenAI has launched next-generation audio models via the API, capable of sophisticated speech recognition and customized speech synthesis.
OpenAI has revealed the technical principles behind Voice Engine, which generates custom voices from a 15-second audio sample, along with details of its safety research.
OpenAI has unveiled early use cases and a safe deployment approach for **Voice Engine**, which generates natural-sounding voices from just a 15-second sample.
Covers how to optimize inference performance and memory efficiency of the Bark TTS model using Hugging Face's Optimum and Accelerate.
SpeechT5, a unified speech processing model, has been added to the Hugging Face Transformers library.