OpenSkillIndex← back to search
claude-codeopenclawautomation

Skills aimlapi-voice

Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script with retries and polling.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/aimlapihello/aiml-voice" ~/.claude/skills/openclaw-skills-aimlapi-voice && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/aimlapihello/aiml-voice" ~/.openclaw/skills/openclaw-skills-aimlapi-voice && rm -rf "$T"
manifest: skills/aimlapihello/aiml-voice/SKILL.md
tags
#audio-transcription#speech-to-text#aimlapi#python#voice#automation
source content

AIMLAPI Voice Transcription

Overview

A robust skill for transcribing audio via AIMLAPI's specialized speech-to-text endpoints. It handles queuing, polling for results, and automatic MIME-type detection.

Quick Start

# Set your API key first (if not in env)
# export AIMLAPI_API_KEY="your-key-here"

# Transcribe a file
python {baseDir}/scripts/transcribe.py path/to/audio.ogg

Tasks

Process Voice Messages

When an audio file is received, use this script to extract the text.

python {baseDir}/scripts/transcribe.py <file_path> \
  --model "#g1_whisper-medium" \
  --verbose

Arguments

  • file
    : (Required) Path to the audio file.
  • --model
    : Model ID (default: 
    #g1_whisper-medium
    ).
  • --out
    : Path to save the transcript text.
  • --poll-interval
    : Seconds between status checks (default: 5).
  • --max-wait
    : Stop waiting after N seconds (default: 300).

Dependencies

  • Python 3
  • AIMLAPI_API_KEY
    set in environment or provided via 
    --apikey-file
    .