morioka/tiny-openai-whisper-api

OpenAI Whisper API-style local server, runnig on FastAPI

46
/ 100
Emerging

This tool helps organizations convert spoken audio recordings into text transcripts securely within their own network. You provide an audio file, and it outputs the transcribed text, mimicking the popular OpenAI Whisper API. This is ideal for IT teams or data scientists in organizations that need to process sensitive audio data without sending it to external cloud services due to security policies or network restrictions.

No commits in the last 6 months.

Use this if your organization needs to perform speech-to-text transcription of audio files, but security policies or network firewalls prevent direct use of external OpenAI services.

Not ideal if you don't have strict data residency or security requirements and are comfortable using cloud-based speech-to-text services directly.

on-premise AI data security speech transcription internal data processing network security
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

86

Forks

19

Language

Python

License

MIT

Last pushed

Oct 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/morioka/tiny-openai-whisper-api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.