https://repositoryradar.dev/repos New Voice, Vision & Multimodal repos as Repository Radar covers them, newest first. en 2880 Wed, 15 Jul 2026 08:02:53 GMT https://repositoryradar.dev/repo/zackriya-solutions/meetily https://repositoryradar.dev/repo/zackriya-solutions/meetily Voice, Vision & Multimodal Wed, 15 Jul 2026 08:02:53 GMT a meeting notetaker that never leaves your machine · 27k stars · bus factor 1 (solo) https://repositoryradar.dev/repo/roboflow/supervision https://repositoryradar.dev/repo/roboflow/supervision Voice, Vision & Multimodal Wed, 01 Jul 2026 08:03:01 GMT The reusable toolkit that gives an agent eyes · 48k stars · 332k downloads/wk (PyPI) https://repositoryradar.dev/repo/calesthio/openmontage https://repositoryradar.dev/repo/calesthio/openmontage Voice, Vision & Multimodal Wed, 01 Jul 2026 08:03:01 GMT A coding agent reforged into a full video production studio · 43k stars · bus factor 1 (solo) https://repositoryradar.dev/repo/browser-use/video-use https://repositoryradar.dev/repo/browser-use/video-use Voice, Vision & Multimodal Wed, 01 Jul 2026 08:03:01 GMT Edit video with a coding agent, by reading it instead of watching it · 18k stars · bus factor 2 (concentrated) https://repositoryradar.dev/repo/dograh-hq/dograh https://repositoryradar.dev/repo/dograh-hq/dograh Voice, Vision & Multimodal Wed, 03 Jun 2026 08:02:35 GMT Open-source voice-agent platform, the Vapi alternative · 5k stars · bus factor 1 (solo) · understory +15 https://repositoryradar.dev/repo/jamiepine/voicebox https://repositoryradar.dev/repo/jamiepine/voicebox Voice, Vision & Multimodal Wed, 22 Apr 2026 08:02:43 GMT Local-first voice generation platform · 47k stars · bus factor 1 (solo) https://repositoryradar.dev/repo/ruvnet/ruview https://repositoryradar.dev/repo/ruvnet/ruview Voice, Vision & Multimodal Wed, 11 Mar 2026 09:00:13 GMT WiFi Signals as an Invisible Sensor · 87k stars · bus factor 1 (solo) · understory +3 https://repositoryradar.dev/repo/kittenml/kittentts https://repositoryradar.dev/repo/kittenml/kittentts Voice, Vision & Multimodal Wed, 25 Feb 2026 09:00:21 GMT Lightweight text-to-speech for local AI workflows · 15k stars · bus factor 2 (concentrated) https://repositoryradar.dev/repo/paddlepaddle/paddleocr https://repositoryradar.dev/repo/paddlepaddle/paddleocr Voice, Vision & Multimodal Wed, 12 Nov 2025 09:01:43 GMT Industry-grade OCR & document AI toolkit · 86k stars · 749k downloads/wk (PyPI) · bus factor 2 (concentrated) https://repositoryradar.dev/repo/drewthomasson/ebook2audiobook https://repositoryradar.dev/repo/drewthomasson/ebook2audiobook Voice, Vision & Multimodal Wed, 12 Nov 2025 09:01:43 GMT Convert any eBook into a natural AI-narrated audiobook · 20k stars · 28 downloads/wk (PyPI) · bus factor 1 (solo) · understory +40 https://repositoryradar.dev/repo/immich-app/immich https://repositoryradar.dev/repo/immich-app/immich Voice, Vision & Multimodal Wed, 29 Oct 2025 09:02:50 GMT self-hosted photo and video management · 109k stars · bus factor 9 (distributed) · understory +14 https://repositoryradar.dev/repo/corentinj/real-time-voice-cloning https://repositoryradar.dev/repo/corentinj/real-time-voice-cloning Voice, Vision & Multimodal Wed, 17 Sep 2025 08:04:25 GMT Instant Voice Cloning · 60k stars https://repositoryradar.dev/repo/resemble-ai/chatterbox https://repositoryradar.dev/repo/resemble-ai/chatterbox Voice, Vision & Multimodal Wed, 03 Sep 2025 08:01:52 GMT Open Source TTS with Emotion Control · 26k stars · 52k downloads/wk (PyPI) · bus factor 5 (distributed) https://repositoryradar.dev/repo/microsoft/vibevoice https://repositoryradar.dev/repo/microsoft/vibevoice Voice, Vision & Multimodal Wed, 03 Sep 2025 08:01:52 GMT Long-Form Conversational TTS · 51k stars · 173 downloads/wk (PyPI) · bus factor 4 (distributed) https://repositoryradar.dev/repo/magnitudedev/magnitude https://repositoryradar.dev/repo/magnitudedev/magnitude Voice, Vision & Multimodal Wed, 09 Jul 2025 08:00:16 GMT Vision-Based AI Browser Automation · 34 stars · understory +51 https://repositoryradar.dev/repo/vectorspacelab/omnigen2 https://repositoryradar.dev/repo/vectorspacelab/omnigen2 Voice, Vision & Multimodal Wed, 09 Jul 2025 08:00:16 GMT Multimodal Generation Model for Images & Text · 4k stars https://repositoryradar.dev/repo/koljab/realtimestt https://repositoryradar.dev/repo/koljab/realtimestt Voice, Vision & Multimodal Wed, 25 Jun 2025 08:02:19 GMT Low-Latency Speech-to-Text with Wake Word Activation · 10k stars https://repositoryradar.dev/repo/modelscope/funasr https://repositoryradar.dev/repo/modelscope/funasr Voice, Vision & Multimodal Wed, 30 Apr 2025 08:02:04 GMT A Comprehensive End-to-End Speech Recognition Toolkit · 20k stars · understory +18 https://repositoryradar.dev/repo/omnisvg/omnisvg https://repositoryradar.dev/repo/omnisvg/omnisvg Voice, Vision & Multimodal Wed, 16 Apr 2025 08:10:44 GMT A multimodal generator that uses VLMs to create detailed SVGs, from simple icons to complex anime characters · 3k stars https://repositoryradar.dev/repo/prunaai/pruna https://repositoryradar.dev/repo/prunaai/pruna Voice, Vision & Multimodal Wed, 19 Mar 2025 09:31:14 GMT Model optimization framework that helps developers deliver faster, more efficient models with minimal overhead · 1k stars · 297 downloads/wk (PyPI) · bus factor 2 (concentrated) · understory +6 https://repositoryradar.dev/repo/saiyan-world/goku https://repositoryradar.dev/repo/saiyan-world/goku Voice, Vision & Multimodal Wed, 19 Feb 2025 09:30:54 GMT Flow Based Video Generative Foundation Models · 3k stars