Kolja Beigel

Elite
@KoljaB

Open-source developer of robust, high-performance, real-time STT/TTS pipelines.

RealtimeSTT. Private, real-time speaker diarization on hardware you control. See who is speaking as it happens, no third-party cloud required.

10k

RealtimeTTS. Converts text to speech in realtime

4k

RealtimeVoiceChat. Have a natural, spoken conversation with AI!

3.8k

Linguflex. Command Your World with Voice

812

LocalAIVoiceChat. Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

724

AIVoiceChat. Low latency ai companion voice talk in 60 lines of code using faster_whisper and elevenlabs input streaming

320

TurnVoice. Voice Transformation for Videos. 🎤👄🎬

259

WhoSpeaks. Efficient approach to speaker diarization using voice characteristics extraction

107

LocalEmotionalAIVoiceChat. Simulates talk with an AI that can express emotions

88

stream2sentence. Real-time processing and delivery of sentences from a continuous stream of characters or text chunks.

81

ai_cli_tools. AI at your fingertips: powerful CLI tools for speech, text, and language processing

22

WhoSpeaksLive. Live speaker diarization and transcription for microphone, system audio and YouTube.

14

Revolver. Automatic tool creation and usage

10

vector_companion_fork. A local AI companion that uses a collection of free, open source AI models in order to create two virtual companions that will follow your computer journey wherever you go!

6

SentiMind. AI conversation with emotion

5

KoljaB.

4

ZipVoice-TTS. Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

3

oi-fork. Oi is an open-source cli tool that works on top of codellama and generates code in any editor without extensions.

3

ReadAloud. Mark text or url and let it read out loud

2

github-install-assistant. Automated GitHub repository installation. Smart, LLM-driven, platform-aware CLI tool that handles complex PyTorch/CUDA environments.

2

Retrieval-based-Voice-Conversion-WebUI. Voice data <= 10 mins can also be used to train a good VC model!

1

openai_function_call. Helper functions to create openai function calls w/ pydantic

1

privateGPT. Interact privately with your documents using the power of GPT, 100% privately, no data leaks

1

coqui-ai-TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

1
24
Apply