AI Briefing#tts
The latest AI and developer news about #tts, with the original source and a short summary.
The latest AI and developer news about #tts, with the original source and a short summary.
The 4-bit version requires only 4 GB of VRAM and achieves approximately 13x real-time speed on an RTX 5090.
V4.1-Flash enables server-side tool calls for search, file input, and safety checks, with standalone APIs available for OCR, ASR, and TTS.
Loudness and age tags significantly influence listener preference, while usage metrics and professional status show no correlation with quality.
The 131M parameter model supports 6 languages and 14 voices, achieving 30ms warm start on M5 Max and 0.85% WER on the Open TTS Leaderboard.
The architecture comprises nine layers including ASR, turn-taking, LLM orchestration, and telephony, with Eleven v4 Turbo leading the Artificial Analysis Provider Voice Arena Leaderboard.
Introduces a real-time voice booking bot demo that combines the non-generative model jev with code-based logic to address the latency and hallucination issues of generative LLMs.
The open-source desktop app supports real-time voice conversations, TTS, and ASR using models like Qwen3-TTS and Parakeet TDT v3 without requiring Python.
The model achieves ~1.8% average WER on Open TTS Leaderboard English sets and supports 51 style tags plus zero-shot cloning.
The open-source engine delivers 24 kHz audio with two English voices, scoring 4.46 on UTMOS naturalness evaluations.
It achieved first place overall in the Hume AI benchmark and offers a library of over 2,000 production-ready voices.
Google has unveiled the Gemini 3.8 Flash TTS series, which enables voice generation and cloning via natural language prompts.
The open-source TTS model ViiTorVoice-NAR, which supports partial speech editing, has been released.
Tencent has released AuK-Flash, a 1.5B parameter model that supports fast voice generation and editing via 4-step inference.
The open-source local TTS 'LoudKit', supporting voice cloning and 10 languages, has been released.
VoiceStudio, an open-source tool for performing voice cloning, video dubbing, and transcription locally, has been released.
The ultra-small TTS model sanoTTS with 294k parameters has been released, enabling real-time speech generation even on $3 chips.
TontaubeV1, a 2.9B parameter open-weight TTS model based on character-level tokenization and DualCodec, has been released.
Vellium v1.1.0 released an update supporting local STT/TTS and automatic llama.cpp detection.
Tontaube has released TontaubeV1, a 2.9B parameter open-source TTS model specialized for long-form generation and low-latency inference.
Prosody, comprising rhythm, intonation, and stress patterns, is a core element of TTS models that determines the human-likeness of AI voices.
The local audio AI framework audio.cpp 0.7 has been released, supporting 62 model families and an Arena UI for comparison.
The 120-million-parameter open-source TTS model Sopro V2 delivers SOTA-level voice cloning performance and enables fast inference even on CPUs.
Optimized Qwen3-TTS to achieve sub-50ms latency and 10 RPS throughput on a single H100.
Speko is a gateway service that optimally routes various voice AI models based on performance and cost.