speech-to-text

Transcribe audio files via 0G Compute Network providers using Whisper Large V3.

Updated Apr 26, 2026

Search Tags:#transcription #whisper #audio #headers #formdata #compute-network

Ready to run

npx skills add https://github.com/gabrielfior/ai-village-open-agents --skill speech-to-text-gabrielfior

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speech-to-text
Source: https://github.com/gabrielfior/ai-village-open-agents/tree/main/.opencode/skills/speech-to-text
Command: npx skills add https://github.com/gabrielfior/ai-village-open-agents --skill speech-to-text-gabrielfior

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio files quickly and accurately using distributed compute providers (Whisper Large V3), turning speech into searchable text for transcripts, captions, and data extraction.

Core Features & Use Cases

Transcription of diverse audio formats (mp3, wav, ogg, flac, webm) to JSON, text, or SRT subtitles.
Handles metadata like language and optional settings via model parameter and headers.
Use Case: Automatically generate transcripts for meetings, podcasts, or interviews and store results for analytics.

Quick Start

Transcribe a sample audio file using the Whisper-based service provider and retrieve the transcript in JSON.

Frequently Asked Questions about speech-to-text

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe audio files into text using Whisper?▼

Transcribe audio by uploading files via FormData to a 0G Compute Network provider running Whisper Large V3, which processes the speech and returns accurate text transcripts.

What audio formats are supported for speech-to-text transcription?▼

Speech-to-text transcription supports mp3, wav, ogg, flac, and webm audio formats, processing them through Whisper to generate text or subtitle outputs.

Can I generate SRT subtitles from audio files?▼

Yes, you can generate SRT subtitles from audio files by configuring the transcription service to output SRT format alongside JSON or plain text options.

How does audio transcription work on the 0G Compute Network?▼

Audio transcription works by sending FormData uploads to distributed compute providers, extracting the ChatID from the ZG-Res-Key header, and calling processResponse with usage data.

Does Whisper speech-to-text support language metadata for transcription?▼

Yes, Whisper speech-to-text supports language metadata and optional transcription settings passed via the model parameter and headers to guide the audio processing.

What is the best way to transcribe podcasts or interviews into searchable text?▼

The best way to transcribe podcasts or interviews is using Whisper Large V3 on 0G Compute to convert speech into searchable text, JSON data, or SRT subtitle formats.