Similar to This
GitHub - TacoTakumi/VoiceManager: A low latency streaming STT / STT server ...
GitHub - TacoTakumi/VoiceManager: A low latency streaming STT / STT server to add a voice to your LLM. Also supports batch mode.
github.com/TacoTakumi/VoiceManager
I added Piper to Home Assistant for local AI voice control ...
I added Piper to Home Assistant for local AI voice control, but it turned out to be even more useful
xda-developers.com/i-added-piper-to-home-assistant-for-local-ai-voice-control-but-it-turned-out-to-be-even-moreuseful/
Release koboldcpp-1.124 · LostRuins/koboldcpp
Release koboldcpp-1.124 · LostRuins/koboldcpp: KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install. - Release koboldcpp-1 ...
github.com/LostRuins/koboldcpp/releases/tag/v1.124
Google’s new Gemini Live Avatars want to make support bots feel more human
Google’s new Gemini Live Avatars want to make support bots feel more human: Google is rolling out Gemini 3.8 Live with Avatar to bring lip‑synced ...
androidauthority.com/gemini-live-avatar-3715280/
Gemini can now clone your voice and perform scripts like an actor
Gemini can now clone your voice and perform scripts like an actor: Google’s Gemini 3.8 Flash TTS can create custom voices, replicate authorized voices ...
androidauthority.com/gemini-3-8-flash-text-to-speech-rolling-out-3714915/
OpenAI makes you call sales for a custom voice. Google just made it ...
OpenAI makes you call sales for a custom voice. Google just made it self-serve.: Google's Gemini 3.8 TTS lets developers design a voice from a text prompt ...
thenewstack.io/gemini-tts-voice-replication-api/
Qwen 3 TTS and Voicebox: Who's speaking there? - | Golem.de
Qwen 3 TTS and Voicebox: Who's speaking there? - | Golem.de: Qwen 3 TTS is good at converting German text into spoken language and imitating voices from ...
golem.de/news/qwen-3-tts-und-voicebox-wer-spricht-denn-da-2608-211669.html
Smallest.ai raises $13M to build ultra-fast voice AI that sounds genuinely ...
Smallest.ai raises $13M to build ultra-fast voice AI that sounds genuinely human: The startup is building voice models designed to make AI phone calls pass the ...
techcrunch.com/2026/07/31/smallest-ai-raises-13m-to-build-ultra-fast-voice-ai-that-sounds-genuinely-human/
The Gemini app’s mic just got a major upgrade for multilingual users
The Gemini app’s mic just got a major upgrade for multilingual users: The voice input feature in the Gemini app is getting support for over 70 languages ...
androidauthority.com/gemini-app-mic-voice-input-new-languages-3678300/
GitHub - groxaxo/Local-VoiceMode-LLM: Local ears and mouth for your LLM — ...
GitHub - groxaxo/Local-VoiceMode-LLM: Local ears and mouth for your LLM — offline, private, safe, free & open source. Voice-enable any local LLM stack: Claude ...
github.com/groxaxo/Local-VoiceMode-LLM
GitHub - groxaxo/opencode-voice-service: Silero VAD-driven voice ...
GitHub - groxaxo/opencode-voice-service: Silero VAD-driven voice conversation service + opencode skill
github.com/groxaxo/opencode-voice-service
Google Unveils Gemini 3.1 Flash TTS for Enhanced AI Speech Quality
Google Unveils Gemini 3.1 Flash TTS for Enhanced AI Speech Quality: Discover how Google's Gemini 3.1 Flash TTS technology revolutionizes AI speech quality ...
smallbiztrends.com/google-unveils-gemini-3-1-flash-tts-for-enhanced-ai-speech-quality/
GitHub - Al0olo/voxtral-voice-clone: Training the missing codec encoder ...
GitHub - Al0olo/voxtral-voice-clone: Training the missing codec encoder for Mistral's Voxtral-4B-TTS, enabling zero-shot voice cloning
github.com/Al0olo/voxtral-voice-clone
GitHub - mozi1924/Qwen3-TTS-EasyFinetuning: Easy fine-tuning for ...
GitHub - mozi1924/Qwen3-TTS-EasyFinetuning: Easy fine-tuning for Qwen3-TTS: Fast voice cloning and high-quality multilingual speech synthesis.
github.com/mozi1924/Qwen3-TTS-EasyFinetuning
GitHub - FartyPants/kitten_tts_local_mcp_server: Local MPC server using ...
GitHub - FartyPants/kitten_tts_local_mcp_server: Local MPC server using Kitten TTS (Windows, ONNX)
github.com/FartyPants/kitten_tts_local_mcp_server
GitHub - QwenLM/Qwen3-TTS: Qwen3-TTS is an open-source series of TTS ...
GitHub - QwenLM/Qwen3-TTS: Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive ...
github.com/QwenLM/Qwen3-TTS
GitHub - bc-dunia/qwen3-TTS-studio: A professional-grade interface for ...
GitHub - bc-dunia/qwen3-TTS-studio: A professional-grade interface for Qwen3-TTS, designed to unlock the model's full potential with fine-grained control ...
github.com/bc-dunia/qwen3-TTS-studio
GitHub - agentem-ai/izwi: A local audio inference engine
GitHub - agentem-ai/izwi: A local audio inference engine: A local audio inference engine. Contribute to agentem-ai/izwi development by creating an account on ...
github.com/agentem-ai/izwi