THE DUDE’S FIELD GUIDE
Open-source Speech & transcription
Speech and transcription projects turn speech into text or text into speech. Choose based on language coverage, speaker needs and whether processing must stay on your machine.
How to choose
Check model size, real-time versus batch support, timestamps and GPU requirements. Test on representative audio; accents and background noise can affect results.
Repositories to explore
Ordered by observed stars. This is a directory sample, not a best-to-worst verdict. Individual briefs show observation dates and source links.
| Project and purpose | Code license | Setup | Observed stars |
|---|---|---|---|
| huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. | Apache-2.0 | Developer library | 169,3292026-11-17 |
| openai/whisper The speech model behind many transcription tools. | MIT | Command line | 113,1042026-11-17 |
| ggml-org/whisper.cpp Run speech recognition on your own machine. | MIT | Command line | 55,2712026-11-17 |
| SYSTRAN/faster-whisper Turn speech into text with a Python workflow. | MIT | Developer tool | 26,8342026-11-17 |
| m-bain/whisperX Add word timing and speaker labels to transcripts. | BSD-2-Clause | Command line | 25,4162026-11-17 |
| modelscope/FunASR Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving. | MIT | Developer library | 21,0612026-11-17 |
| leon-ai/leon 🧠 Leon is your open-source personal assistant. | MIT | See setup guide | 17,6922026-11-18 |
| livekit/agents Build realtime voice agents with speech and model integrations. | Apache-2.0 | Developer library | 15,2742026-11-18 |
| alphacep/vosk-api Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node | Apache-2.0 | See setup guide | 15,2702026-11-17 |
| abus-aikorea/voice-pro Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal… | GPL-3.0 | Web app | 13,4452026-11-17 |
| PaddlePaddle/PaddleSpeech Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and… | Apache-2.0 | Developer library | 12,7142026-11-17 |
| speechbrain/speechbrain A PyTorch-based Speech Toolkit | Apache-2.0 | Developer library | 11,9402026-11-17 |
| QuentinFuxa/WhisperLiveKit Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs. | Apache-2.0 | See setup guide | 11,2582026-11-17 |
| openvinotoolkit/openvino OpenVINO™ is an open source toolkit for optimizing and deploying AI inference | Apache-2.0 | Developer library | 11,1892026-11-17 |
| espnet/espnet End-to-End Speech Processing Toolkit | Apache-2.0 | Developer library | 10,0202026-11-17 |
| QwenAudio/SenseVoice Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection. | MIT | See setup guide | 9,7742026-11-17 |
| Uberi/speech_recognition Speech recognition module for Python, supporting several engines and APIs, online and offline. | BSD-3-Clause | See setup guide | 9,0052026-11-17 |
| nl8590687/ASRT_SpeechRecognition A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统 | GPL-3.0 | See setup guide | 8,4062026-11-17 |
| Neywa-Labs/mlx-audio A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. | MIT | Developer library | 8,3012026-11-18 |
| anomalyco/hex Local voice dictation for mac, windows and linux | MIT | See setup guide | 7,2622026-11-17 |
| TalAter/annyang 💬 Speech recognition for your site | MIT | See setup guide | 6,8212026-11-17 |
| modelscope/FunClip FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI. | MIT | See setup guide | 6,5712026-11-17 |
| argmaxinc/argmax-oss-swift On-device Speech AI for Apple Silicon | MIT | See setup guide | 6,4602026-11-17 |
| PaddlePaddle/PaddleX All-in-One Development Tool based on PaddlePaddle | Apache-2.0 | See setup guide | 6,2972026-11-17 |
| MahmoudAshraf97/whisper-diarization Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper | BSD-2-Clause | See setup guide | 5,6772026-11-17 |
| wenet-e2e/wenet Production First and Production Ready End-to-End Speech Recognition Toolkit | Apache-2.0 | Developer library | 5,2562026-11-17 |
| mkiol/dsnote Transcribe, read aloud and translate notes on your own device. | MPL-2.0 | Desktop app | 1,7202026-11-18 |
Is open source the same as free to run?
No. The code license and operating costs are separate. Check model terms, hardware, hosting and paid services in each project’s documentation.
Read our sourcing and ranking methodology →