oatda-transcribe-audio

OATDA Audio Transcription

Transcribe audio files to text through OATDA's unified audio API.

When to Use

Use this skill when the user wants to:

• Transcribe meetings, podcasts, interviews, or voice notes
• Convert speech audio to written text
• Create subtitles or timestamped transcripts
• Use Whisper-style speech-to-text models through OATDA
• Use the OATDA transcribe_audio capability

Prerequisites

The user needs an OATDA API key. Check in this order:

1. $OATDA_API_KEY environment variable
2. ~/.oatda/credentials.json config file

If neither exists, tell the user:

You need an OATDA API key. Get one at https://oatda.com, then set it: export OATDA_API_KEY=your_key_here

Step-by-Step Instructions

1. Resolve the API key

# Check env var first; if empty, auto-load from credentials file
if [[ -z "$OATDA_API_KEY" ]]; then
  export OATDA_API_KEY=$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)
fi

# Verify key exists (show first 8 chars only)
echo "${OATDA_API_KEY:0:8}"

If the output is empty or null, stop and ask the user to configure their API key.

IMPORTANT:

• Never print the full API key. Only show the first 8 characters for verification.
• The key resolution script and subsequent curl commands must run in the same shell session. Each separate bash/terminal invocation starts with an isolated environment where previously exported variables are lost. Either run all commands in one session, or chain them.

2. Determine the model

Map common aliases:

User says	Provider	Model
whisper, whisper-1, openai whisper (default)	openai	whisper-1
transcription, speech to text, stt	openai	whisper-1

Default: openai / whisper-1 if no model is specified.

If the user provides provider/model format directly (e.g., openai/whisper-1), split on / to get separate provider and model values.

3. Prepare the audio input