Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
LFM3-Audio-2B
Modelsany to any model by LiquidAI · transformers
LiquidAI/LFM3-Audio-2B -
PiVo-1.4M
Modelstext to speech model by empero-ai · onnx
empero-ai/PiVo-1.4M -
SOV-Transcribe-1
Modelsautomatic speech recognition model by salesforce-sovereign-intelligence · transformers
salesforce-sovereign-intelligence/SOV-Transcribe-1 -
Underdog-Bark-3.0-Pro
Modelsautomatic speech recognition model by ConwayResearch · transformers
ConwayResearch/Underdog-Bark-3.0-Pro -
ai-podcast-voiceover-skill
SkillsAI podcast voiceover agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn an article, notes, or a finished script into a solo podcast episode with a consistent host voice, natural pacing, pronunciation control, and a ready-to-publish audio file. AI播客配音 · 文章转播客
git clone https://github.com/beatra-ai/ai-podcast-voiceover-skill.git -
Earlybird-29M
Modelsautomatic speech recognition model by sahilmahendrakar · transformers
sahilmahendrakar/Earlybird-29M -
awesome-selfhosted-ai
AI repositoriesCurated list of self-hosted open-source AI: local LLMs, chat UIs, agents, MCP servers, RAG, speech and image generation. Health-checked weekly, dead projects removed automatically.
git clone https://github.com/glincker/awesome-selfhosted-ai.git -
phonon-40m-multilingual
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-multilingual -
Inflect-Mini-v3
Modelstext to speech model by owensong
owensong/Inflect-Mini-v3 -
antalia-mini
Modelstext to speech model by cloud0day3 · antalia-mini
cloud0day3/antalia-mini -
substack-mcp
MCP serversMCP server for Substack: rich drafts, Notes, analytics, and consented subscriber management across publications. Long-form posts stay draft-only; Notes publish immediately. Used regularly by multiple newsletters, includes a CLI.
git clone https://github.com/conorbronsdon/substack-mcp.git -
chatterbox-farsi
Modelstext to speech model by mehdi-hf · chatterbox
mehdi-hf/chatterbox-farsi -
AuroraASR-1M
Modelsautomatic speech recognition model by AuroraAI-Research · transformers
AuroraAI-Research/AuroraASR-1M -
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-labs-unified-asr-0.6b -
Phonon-2.5
Modelsautomatic speech recognition model by FermionResearch · mlx
FermionResearch/Phonon-2.5 -
hurston-1
Modelstext to speech model by destined
destined/hurston-1 -
automatic speech recognition model by mistralai · vllm
mistralai/Voxtral-Mini-4B-Realtime-Arabic -
tiny-audio
Docs & tutorialsA speech-to-text system you can train for $25. A frozen speech encoder and a Qwen LLM joined by a small trained projector, with word timestamps, speaker diarization, a batched HTTP server, a live demo, and a free course.
git clone https://github.com/alexkroman/tiny-audio.git -
Drama-3-ComfyUI
Modelstext to speech model by PedroMarinhoDev
PedroMarinhoDev/Drama-3-ComfyUI -
Mach-Boom
Modelstext to speech model by SyzygyResearch
SyzygyResearch/Mach-Boom -
voice-ai
Agents & frameworksRapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
git clone https://github.com/rapidaai/voice-ai.git -
awesome-voice-typing
Docs & tutorialsCurated list of open-source speech-to-text and voice typing tools for Linux, macOS, Windows, Android, and iOS. Offline, local, and cloud.
git clone https://github.com/primaprashant/awesome-voice-typing.git -
Duyu-small
Modelsautomatic speech recognition model by KaanAydinli · duyu-small
KaanAydinli/Duyu-small -
Llamatik
AI repositoriesTrue on-device AI SDK for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM inference, Speech-to-Text, Image Generation, Agent Framework and RAG — powered by llama.cpp, whisper.cpp and stable-diffusion.cpp.
git clone https://github.com/llamatik/Llamatik.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.