Oatda Generate Speech

Generate speech or audio from text using OATDA's unified audio API. Triggers when the user wants to convert text to speech, create narration, voiceovers, acc...

Security Scan

The skill's requirements and runtime instructions are consistent with a text→speech integration: it needs an OATDA API key, curl and jq, and reads a local OATDA credentials file to obtain the key.

Purpose & Capability

Name and description are TTS-focused and the declared requirements (curl, jq, OATDA_API_KEY, ~/.oatda/credentials.json) are appropriate and expected for calling the OATDA HTTP API and extracting a stored API key.

Instruction Scope

SKILL.md only instructs using curl and jq to call OATDA endpoints and to resolve the API key from either OATDA_API_KEY or ~/.oatda/credentials.json. Reading the local credentials file is expected for convenience, but it's a sensitive operation: ensure the credentials file contains only the OATDA key and that the agent will not print the full key. The jq expression used to extract the key may be brittle if the file format differs.

Install Mechanism

No install spec (instruction-only), so nothing is written to disk or downloaded. This is low risk and appropriate for a simple wrapper around curl/jq.

Credentials

Only a single provider credential (OATDA_API_KEY) and an expected config path are requested. Requiring either an env var or reading ~/.oatda/credentials.json is proportionate to the stated functionality.

Persistence & Privilege

always is false and the skill does not request system-wide changes or modify other skills. Autonomous invocation is allowed by default but combined with the limited scope here it does not raise additional red flags.

Assessment

This skill appears to do only what it says: call OATDA's speech API. Before installing, confirm you trust oatda.com and inspect ~/.oatda/credentials.json to verify it contains only the OATDA key. If you are cautious, set OATDA_API_KEY in the environment instead of relying on a credentials file, restrict the key's permissions if possible, and avoid pasting the full key into chat or logs. Also test with a limited or expendable key to verify behavior. If your credentials file has unexpected contents or other secrets, do not install/use the skill until you remediate that file.

OATDA Speech Generation

Generate spoken audio from 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
tts, tts-1, openai tts (default)	openai	tts-1
tts hd, tts-1-hd	openai	tts-1-hd
gpt tts, gpt-4o mini tts	openai	gpt-4o-mini-tts

Default: openai / tts-1 if no model specified.

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

Common OpenAI voices include alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer. Use alloy if the user does not specify a voice.

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

Discovering Audio Model Parameters

Query available audio models and inspect supported_params before sending optional fields:

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:

• audio_modes containing tts
• supported voice values
• allowed response_format values
• optional fields like instructions or language

API Call

The speech endpoint returns binary audio, not JSON. Always save the response to a file.

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/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "<PROVIDER>",
    "model": "<MODEL>",
    "input": "<TEXT_TO_SPEAK>",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1.0
  }' \
  --output speech.mp3

Common Parameters

• input: Text to convert to speech, max 15000 characters
• voice: Voice name, e.g. alloy, nova, shimmer
• response_format: mp3, opus, aac, flac, wav, pcm, mulaw, or alaw
• speed: 0.25 to 4.0, default 1.0
• instructions: Optional tone/style guidance for supported models
• language: Optional language code for supported models

Success Handling

If the request succeeds, tell the user where the file was saved, for example:

Speech generated successfully: speech.mp3

If headers matter, use curl -D headers.txt while still saving the audio body with --output.

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 format and query oatda-list-models with type=audio
429	Rate limited or monthly cap	Wait briefly and retry once
500	Provider error	Show the error message if returned

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/speech" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "openai",
    "model": "tts-1",
    "input": "Welcome to OATDA, one API to direct all.",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1.0
  }' \
  --output speech.mp3

Notes

• Endpoint: /api/v1/llm/speech
• Use input, not prompt, for TTS requests
• Always save the response with --output
• Use oatda-list-models to discover available audio models
• Equivalent capability name: generate_speech
• Related skills: oatda-list-models, oatda-transcribe-audio, oatda-translate-audio