skills.rest
Military-Veteran-Team-LPT-Realty
Military-Veteran-Team-LPT-RealtyOFFICIAL
Explore all skills by this author →
GitHub

webdev-voice-transcription

Converts speech to text in Manus web and mobile projects using the built-in Whisper API.

Updated Sep 16, 2026
Search Tags:#transcription#audio#fullstack#speech-to-text#expo#manus#whisper api
One-click install
npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill webdev-voice-transcription-military-veteran-team-lpt-realty
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: webdev-voice-transcription
Source: https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills/tree/main/skills/webdev-voice-transcription
Command: npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill webdev-voice-transcription-military-veteran-team-lpt-realty

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Adding speech-to-text to a Manus fullstack web or Expo mobile app normally requires wiring up an external transcription service, managing API keys, and handling audio formats. This Skill provides a preconfigured helper that calls 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, detected ISO-639-1 language, and timestamped segments with metadata. - Optional Accuracy Hints: Pass a language code or context prompt to improve transcription quality. - Use Case: Build a meeting-notes app where the frontend records audio, uploads it to storage, and the backend transcribes the recording URL into searchable, timestamped text. ## Quick Start Ask the AI to add voice transcription to your Manus webdev or mobile project by transcribing an uploaded audio file URL with the built-in Whisper helper.

Frequently Asked Questions about webdev-voice-transcription

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

FAQPage Schema
How do I add speech-to-text to a Manus webdev project?▼

Import transcribeAudio from server/_core/voiceTranscription and pass it the URL of an uploaded audio file. The helper calls the built-in Whisper API and returns the transcription text, detected language, and timestamped segments with no manual setup.

What audio formats does Whisper transcription support?▼

The transcription helper accepts webm, mp3, wav, ogg, and m4a files. The audio must be pre-uploaded to storage and referenced by 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 and storage upload, then the backend transcribes the file URL.

How do I improve Whisper transcription accuracy?▼

Pass the optional language parameter with an ISO-639-1 code and a prompt string giving context, 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?▼

It only accepts URLs to pre-uploaded audio files, not raw uploads or live streams, and enforces a 16MB size limit. The frontend must handle audio capture, storage upload, and size validation before calling it.

Related Skills

Explore More Software Engineering Skills→
team-telnyxteam-telnyx
3

telnyx-stt

Transcribe MP3, WAV, OGG, M4A, and WebM audio files via the Telnyx Speech-to-Text API.

Official
Basic
inference-shinference-sh
688

speech-to-text

Transcribe audio files into text with timestamps using Whisper models.

Official
Intermediate
panyeroa1panyeroa1

Meeting Summarizer

Transcribe and summarize multi-language meetings into markdown, PDF, or JSON.

Community
Advanced
anicca-labsanicca-labs

speech-recognition

Facilitate on-device voice-to-text dictation on iOS and Android using expo-speech-recognition.

Official
Intermediate