Self-hosted alternatives to Live Speaker Diarization
200 self-hosted apps like Live Speaker Diarization, closest match first.
Top picks
- A

AsrServe
LaunchSelf-hosted realtime and offline ASR with SOTA open models, speaker diarization and an OpenAI-compatible API. GPU, CPU, macOS Apple Silicon.
Open sourceSelf-hosted
- O

OpenTranscribe
LaunchSelf-hosted AI-powered transcription platform with speaker diarization, search, and collaboration features. Built with Svelte, FastAPI, and Docker for easy deployment.
Open sourceSelf-hosted
- P
PolyTalk
LaunchPolyTalk delivers self-hosted, real-time speech-to-speech translation, no cloud, sub-second latency, 40+ languages, fully open source.
Open sourceSelf-hosted
- S

Streamcore Server
LaunchStreamCore is an open-source server for realtime voice agents. It handles live audio over WebRTC, with the WHIP protocol for sending audio in, and runs speech-to-text, language model and text-to-speech steps as a streaming pipeline. Users c
Open sourceSelf-hosted
- D
Dia-TTS-Server
LaunchSelf-host the powerful Dia TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), support for SafeTensors/BF16, voice cloning, dialogue generation, and GPU/CPU execution.
Open sourceSelf-hosted
- S
Scriberr
LaunchScriberr is a self-hostable, offline audio transcription app. It runs state-of-the-art speech recognition models on your own machine, so the audio and transcripts never have to leave it. You can choose between NVIDIA Parakeet and Canary mod
Open sourceSelf-hosted
More like Live Speaker Diarization
Willow Inference Server
Open source, local, and self-hosted highly optimized language inference…
Self-Hosted AI Stack
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document…
Whisper Website
Self-hosted web application, which can be used to convert audio to subtitles…
OmniKey-AI-Unified-Key-Manager
A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini…
About Live Speaker Diarization
Live Speaker Diarization
Live Speaker Diarization
The Multilingual Live Mic tab uses Nemotron 3.5 multilingual streaming ASR with Nemotron-3-Diarization. It shares the microphone controls, speaker activity lanes, and transcript display with Live Mic, while using the separate /api/diarization/multilingual/stream relay. Language is detected automatically by the deployed model. Start the microphone and wait for Live before speaking.
- Price
- Free
- Made by
- nvidia
- Category
- AI
- Website
- huggingface.co/spaces/nvidia/nemotron-diarization

