Toolverse
All skills
Data Science

add-voice-transcription

by gavrielc

Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Author
gavrielc
Category
Data Science
Views
1
GitHub repo

About this skill

Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

How to use

  1. Sprawdź, czy plik src/transcription.ts już istnieje w projekcie. Jeśli tak, przejdź do kroku 5. Jeśli nie, kontynuuj instalację.

  2. Upewnij się, że masz klucz API OpenAI dla usługi Whisper. Jeśli go nie masz, przejdź na https://platform.openai.com/api-keys i utwórz nowy klucz. Przechowaj go bezpiecznie — będzie potrzebny w dalszych krokach.

  3. Dodaj zdalne repozytorium WhatsApp do projektu, jeśli jeszcze go nie masz: git remote add whatsapp https://github.com/qwibitai/nanoclaw-whatsapp.git. Następnie pobierz gałąź z umiejętnością transkrypcji: git fetch whatsapp skill/voice-transcription i scal ją: git merge whatsapp/skill/voice-transcription. Jeśli pojawią się konflikty w pliku package-lock.json, zaakceptuj wersję ze scalenia: git checkout --theirs package-lock.json && git add package-lock.json && git merge --continue.

  4. Zainstaluj zależności i zbuduj projekt: npm install --legacy-peer-deps oraz npm run build. Uruchom testy, aby upewnić się, że wszystko działa: npx vitest.

  5. Dodaj swój klucz API OpenAI do pliku .env: OPENAI_API_KEY=twoj_klucz_tutaj. Od tego momentu wiadomości głosowe przesyłane przez WhatsApp będą automatycznie transkrybowane i dostarczone agentowi jako tekst.

Related skills

quant-analyst

by zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

Data Science
67217

xlsx

by anthropics

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2)

Data Science
40128

arxiv-search

by langchain-ai

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Data Science
76172

pdf-processing

by Ming-Kai-LC

Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.

Data Science
23134

skill-creator

by anthropics

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Data Science
59147

pdf

by anthropics

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Data Science
31144