Oatda Transcribe Audio

OATDA Audio Transcription

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

API Key Resolution

All commands need the OATDA API key. Resolve it inline for each exec call:

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}"

If the key is empty or null, tell the user to get one at https://oatda.com and configure it.

Security: Never print the full API key. Only verify existence or show first 8 chars.

Model Mapping

| 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 specified.

If the user provides provider/model format directly (for example openai/whisper-1), split on /.

> ⚠️ Models change over time. If a model ID fails, query oatda-list-models with ?type=audio first.

Input Preparation

The transcription endpoint supports:

Maximum audio file size is 25MB.

For local files, prefer multipart upload because it is simpler and avoids large JSON bodies.

Discovering Audio Model Parameters

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X GET "https://oatda.com/api/v1/llm/models?type=audio" \
  -H "Authorization: Bearer $OATDA_API_KEY" | jq '.audio_models[] | {id, supported_params}'

Look for:

API Call (multipart)

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/transcriptions" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -F "provider=" \
  -F "model=" \
  -F "file=@" \
  -F "response_format=json"

Alternative API Call (base64 JSON)

AUDIO_DATA_URL="data:audio/mpeg;base64,$(base64 -w 0 audio.mp3)"
export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/transcriptions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d "$(jq -n \
    --arg provider \"\" \
    --arg model \"\" \
    --arg file \"$AUDIO_DATA_URL\" \
    '{provider: $provider, model: $model, file: $file, response_format: \"json\"}')"

Common Parameters

Response Format

The API returns JSON like:

{
  "text": "The transcribed text...",
  "language": "en",
  "duration": 42.5,
  "segments": [],
  "words": [],
  "costs": {
    "inputCost": 0,
    "outputCost": 0.0001,
    "totalCost": 0.0001,
    "currency": "USD"
  }
}

Present the text field to the user. Include subtitles, segments, or words if the requested format includes them.

Error Handling

| HTTP Status | Meaning | Action | |-------------|---------|--------| | 401 | Invalid API key | Tell user to check their key | | 402 | Insufficient credits | Tell user to check balance | | 400 | Bad request / model not supported | Check model or file format and query oatda-list-models with type=audio | | 413 | File too large | Keep audio under 25MB or split it | | 429 | Rate limited or monthly cap | Wait briefly and retry once |

Example

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/transcriptions" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -F "provider=openai" \
  -F "model=whisper-1" \
  -F "file=@meeting.mp3" \
  -F "response_format=json"

Notes

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/transcriptions" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -F "provider=openai" \
  -F "model=whisper-1" \
  -F "file=@meeting.mp3" \
  -F "response_format=json"