General skillMedia, audio and video

indic-voice-pipeline

Download, transcribe, and translate Indic-language audio and video locally.

Stars
1
Forks
0
License
MIT
Updated
Updated Feb 15, 2026

Checking live repository facts…

Project overview

Indic Voice Pipeline combines yt-dlp with fine-tuned Whisper models and Qwen3-ASR to process audio or video in 12 Indian languages and export text, subtitles, and structured JSON. Optional pyannote diarization adds speaker labels and requires a Hugging Face token. Transcription runs locally, though model downloads and hardware demands can be substantial.

Repository facts

Primary language
Python
License
MIT
Repository updated
Feb 15, 2026
Default branch
main

Resource types

General skill

Use cases

Media, audio and videoContent creation

Platforms

Claude Code, Codex, and more

Runtime

Local

Capabilities

Audio processingTranscriptionTranslationVideo processing

Audience

Content creators

Related projects

Browse more similar projects