whisperX-FastAPI and whisper.api

These are competitors offering alternative API wrapper implementations around Whisper-based speech-to-text models, with the first built on WhisperX (optimized for speaker diarization) and the second on a fine-tuned Whisper variant, serving similar use cases of exposing ASR functionality via HTTP endpoints.

whisperX-FastAPI
61
Established
whisper.api
55
Established
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 16/25
Adoption 10/25
Maturity 16/25
Community 13/25
Stars: 174
Forks: 58
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 914
Forks: 38
Downloads:
Commits (30d): 22
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About whisperX-FastAPI

pavelzbornik/whisperX-FastAPI

FastAPI service on top of WhisperX

This tool helps convert audio and video recordings into text transcripts, identifying different speakers and aligning the text with the audio. You provide an audio or video file (like an interview, meeting recording, or lecture) and receive a detailed text output, making it easier to analyze spoken content. Anyone who needs to extract written information from spoken content, such as journalists, researchers, or content creators, would find this useful.

transcription audio-analysis video-processing speaker-diarization content-analysis

About whisper.api

innovatorved/whisper.api

This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR model.

This is a self-hosted API for converting spoken audio into written text. You feed it audio files or live audio streams, and it produces a transcript in formats like JSON, SRT, or VTT. It's designed for developers and technical teams who need to integrate high-performance speech-to-text capabilities directly into their applications or workflows, while keeping full control over their data.

API-development speech-to-text audio-transcription data-privacy application-integration

Scores updated daily from GitHub, PyPI, and npm data. How scores work