Skip to content
RobotWorld
ZH
← Tags

#Tag (11)

WaterfallPagination
Zackriya-Solutions/meetilyMIT

Meetily: Local Meeting Transcription With a Clear Cloud Boundary

A Tauri and Rust desktop meeting assistant that transcribes microphone and system audio locally with Whisper or Parakeet, stores meetings in SQLite, and sends transcript text to the cloud only when a hosted LLM is selected.

LocalFirstSpeechRecognition
Rust32k3.5k132
buxuku/SmartSubMIT

SmartSub: Open-Source One-Stop Desktop Tool for Subtitle Generation, Translation, AI Dubbing & Voice Cloning

SmartSub is an open-source desktop tool (5.5k Stars, MIT license) that packs the entire audio/video subtitle and dubbing pipeline — speech-to-text, translation, proofreading, TTS dubbing, burn-in — into one app. Supports 8 transcription engines (whisper.cpp/faster-whisper/FunASR/Qwen3-ASR/FireRedASR/Parakeet etc.), 20 translation services, local TTS with zero-shot voice cloning. Built-in AI assistant (multimodal visual diagnostics + Agentic tool-calling) and 111 MCP tools + CLI commands for Cursor/Claude Code/Codex integration. Full pipeline runs completely free, cross-platform Windows/macOS/Linux with full GPU acceleration.

SpeechToTextSubtitleTranslation
TypeScript5.5k41727
0xShug0/audio.cppNOASSERTION

audio.cpp: One C++ Runtime for 110+ Local Audio Models

A ggml-based pure C++ audio inference framework that pulls 110+ model families (TTS, voice cloning, voice conversion, speech recognition, diarization, VAD, source separation, codecs and music generation) into one native runtime with CUDA, HIP, Vulkan, Metal and CPU backends, entered through a CLI, an OpenAI-style server, an embedded WebUI and JSON pipelines; same-machine comparisons against Python reference paths show 1.8x to 5x on several TTS routes and up to 37% lower peak VRAM with Q8 packages.

AudioTTS
C++3.5k41133
Ming 3.0 Opens a Full-Stack Audio Stack
0:56

Ming 3.0 Opens a Full-Stack Audio Stack

@Lonely__MH · 85 views · 2026-11-03
Speech & AudioTTS
Nemotron 3.5 Transcribe: One Model for Multilingual Audio
2:00

Nemotron 3.5 Transcribe: One Model for Multilingual Audio

@NVIDIAAI · 121 views · 2026-10-28
NVIDIANemotron
Fluid Speech Mini: Open-Source Dictation ASR Under 300 MB, On-Device
0:46

Fluid Speech Mini: Open-Source Dictation ASR Under 300 MB, On-Device

@FluidVoiceApp · 230 views · 2026-10-13
Speech RecognitionASR
Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars
0:22

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

@axichuhai · 795 views · 2026-09-30
Voice InteractionASR
Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)
0:28

Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)

@_akhaliq · 704 views · 2026-09-30
Audio8 ASR InfiniteStreaming ASR
Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]
0:59

Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]

@FishAudio · 885 views · 2026-09-28
ASRSpeech Recognition
Nemotron 3 Diarization tested: 100M-param real-time speaker diarization, better than expected locally
0:54

Nemotron 3 Diarization tested: 100M-param real-time speaker diarization, better than expected locally

@ouchi · 700 views · 2026-09-27
NVIDIANemotron 3
JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference
0:10

JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference

@nrol_ling · 681 views · 2026-09-22
Speech RecognitionInference Optimization

As an Amazon Associate, we earn from qualifying purchases.