jianchang512/stt

Health v2 · maintenance only

Adoption not part of the score

4766 stars · 499 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

An offline local speech-to-text tool based on faster-whisper models that transcribes audio and video files into JSON, SRT subtitles, or plain text. It runs as a local web app with a browser UI and exposes an API compatible with OpenAI's audio transcription endpoint.

Use cases

• generate srt subtitles from a video offline
• transcribe audio recordings to text locally
• self-host an openai whisper api replacement
• convert lecture recordings into transcripts
• batch transcribe media files with timestamps
• run speech recognition with cuda acceleration on nvidia gpu

When to choose

• you need offline/private transcription without cloud APIs
• you want subtitle files (srt) with timestamps from audio/video
• you want an openai-compatible speech-to-text endpoint you self-host
• you have a local machine, optionally with an NVIDIA GPU

When to avoid

• you need real-time streaming transcription
• you want a cloud-managed service with no local setup
• you need speaker diarization or advanced audio analysis
• you cannot install python/ffmpeg or download whisper models

Facets

application · maturity active

speech-recognition audio-processing video-processing http-server machine-learning speech-processing media self-hosted windows python cross-platform self-hosted faster-whisper subtitles srt offline transcription openai-compatible-api cuda natural-language-processing linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jianchang512/stt")