webdev-voice-transcription

Transcribe audio files to text using the built-in Whisper API helper.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill webdev-voice-transcription-anderhonorato
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: webdev-voice-transcription
Source: https://github.com/AnderHonorato/Mem-rias-IA---Infinity/tree/main/Manus/Skills/webdev-voice-transcription
Command: npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill webdev-voice-transcription-anderhonorato

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Adding speech-to-text to a web or mobile app usually requires configuring an external transcription service, managing API keys, and handling audio pipelines. This Skill provides a preconfigured helper that converts speech to text via the built-in Whisper API with no manual setup. ## Core Features & Use Cases - Preconfigured Transcription Helper: Call transcribeAudio from server/_core/voiceTranscription with an audio URL to get text back. - Rich Whisper Response: Returns the full transcription text, detected language (ISO-639-1), and timestamped segments with metadata. - Optional Accuracy Hints: Pass a language code or context prompt to improve transcription quality. - Use Case: In a Manus fullstack (web-db-user) or Expo mobile app, let users record voice notes, upload the audio to storage, and transcribe the recording into searchable text for meeting notes or voice-driven input. ## Quick Start Ask the AI to transcribe an uploaded audio file by calling the transcribeAudio helper with the file's URL and display the resulting text in the app.

Frequently Asked Questions about webdev-voice-transcription

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

FAQPage Schema
How do I transcribe audio to text with the Whisper API?

Call the transcribeAudio helper from server/_core/voiceTranscription with an audioUrl pointing to a pre-uploaded file. It returns the full transcription text, detected language, and timestamped segments from the native Whisper API response.

What audio formats does Whisper transcription support?

The transcription helper accepts webm, mp3, wav, ogg, and m4a files. The audio must be uploaded to storage first and passed as a URL, with a 16MB file size limit enforced during transcription.

Can I use voice transcription in an Expo mobile app?

Yes, the helper works in Manus mobile-app (Expo) projects as well as fullstack web-db-user projects. The frontend handles audio capture, storage upload, and size validation before calling the transcription function.

How do I improve Whisper transcription accuracy?

Pass the optional language parameter with the expected language code and a prompt parameter with context hints, such as "Transcribe meeting notes". These hints help the Whisper API produce more accurate results.

What are the limitations of the built-in voice transcription helper?

The helper enforces a 16MB file size limit and requires audio to be pre-uploaded and accessible via URL. It does not handle audio capture or storage upload itself; the frontend must manage those steps.