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.
NVIDIA has released Magpie TTS, an open-weight model supporting 12 languages.
NVIDIA supports on-device execution by quantizing ASR, TTS, and speech codecs to GGUF.
A fine-tuning toolkit has been released that lets the ultra-compact TTS model Inflect-Nano-v2 be trained on a specific voice or language.
Inflect-Micro-v2, a highly efficient TTS model capable of local execution with fewer than 10 million parameters, has been released.
audio.cpp 0.4 adds Higgs Audio v3 TTS and Fish Audio S2 Pro among others, now supporting 35 model families with Q8 GGUF improving speed and VRAM.
Neuphonic has open-sourced NeuTTS-2E, a 125M-parameter on-device TTS model capable of controlling 7 emotions.
Hume AI has launched Real World VoiceEQ, a new benchmark that evaluates emotional understanding and naturalness in voice AI.
Explains how to combine Twilio, ElevenLabs, and an LLM to build a voice agent capable of real-time voice responses in 20 minutes.
AI Calling is a next-generation calling technology that combines LLMs with voice technology to have natural conversations with customers.
This introduces how to implement high-quality local TTS even on CPU environments using Kokoro, a lightweight 82M-parameter model.
Gepard 1.0, a 0.6B-parameter streaming TTS model optimized for real-time conversation, has been released as open source.
Vercel AI Gateway now supports real-time voice agents, TTS, and STT capabilities, available in beta through AI SDK 7.
audio.cpp, a ggml-based C++ audio inference framework, has been released, offering up to 5x faster speed compared to Python.
This covers how to measure and optimize per-stage latency in the pipeline to reduce TTFA, which determines how fast a voice agent responds.
This presents 6 key evaluation framework pillars for accurately measuring the performance of voice agents.
Zyphra has launched ZONOS2, an open-source MoE-based TTS model capable of high-fidelity voice cloning and real-time inference.
RedNote has released dots.tts, a SOTA TTS model with 2B parameters under the Apache 2.0 license.
Microsoft has launched MAI-Voice-2, a TTS model supporting 15 languages and voice cloning.
xAI's **Grok** has been adopted as the default voice engine for **Vapi** platform's 12 core voices.
A real-time TTS and voice cloning model supporting sub-60ms low latency and self-hosting has been released.
MOSS-TTS-v1.5 is a TTS model with improved multilingual synthesis performance and voice cloning stability.
This introduces how to build an ElevenAgents voice agent in half a day using Claude Code and connect it to an actual phone call.
OpenReader v3.0, an open-source document reader that supports various AI TTS engines and can produce audiobooks, has been released.
Supertonic 3 has been released as an on-device TTS supporting 31 languages and emotion tags.