» Tag
text-to-speech
5 postsEmotion on cloned voices in Qwen3-TTS: a 25 MB graft and steering vectors
A new 25 MB .qvoice graft format brings emotion control to cloned voices in Qwen3-TTS. Combining steering vectors with CSP fine-tuning preserves timbre while enabling six core emotions plus seven emotion blends.
OmniVoice Studio: Open-Source ElevenLabs Alternative for macOS
OmniVoice Studio is an open-source AI voice application for macOS. It offers a local alternative to ElevenLabs, running entirely on your machine.
Inflect v2: Two ultra-tiny TTS models with 4M and 10M parameters
Inflect v2 introduces ultra-tiny TTS models with 4M and 10M parameters, enhancing usability.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comSpeech-to-Text Accuracy in 2026: Open-Weight vs. Cloud
A study in 2026 benchmarks speech-to-text accuracy across engines, revealing performance variations. Key insights for engineers.
Audio8-TTS-Preview-0.6B: Compact Multilingual Voice Cloning Model
Audio8-TTS-Preview-0.6B is an ideal model for multilingual voice cloning and low-latency speech synthesis.