---
name: sonichi-openai-tts
description: "Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes."
license: "MIT"
metadata:
  decimalai-skill-id: "38b10f3c-2063-4265-bf24-6624d18d0579"
  decimalai-version-id: "d0c50cfa-84e2-4921-a11e-c55f8d5fadcd"
  decimalai-version: "1"
  decimalai-body-sha256: "8475166c829cabf32c8a1e1bc542b9b8eb58b4bbac9fbca4fbe7285fd93a047b"
  decimalai-name: "sonichi/openai-tts"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "design-media"
  decimalai-source: "https://app.decimal.ai/s/sonichi-openai-tts@1/SKILL.md"
---
# OpenAI TTS

Synthesize speech via OpenAI `tts-1-hd`. Reads `OPENAI_API_KEY` from `.env`.

This is offline synthesis — distinct from voice-agent's bidirectional Gemini Live audio.

**Usage**: `/openai-tts [text]`

ARGUMENTS: $ARGUMENTS

## Voices

`alloy`, `ash`, `coral` (default), `echo`, `fable`, `nova`, `onyx`, `sage`, `shimmer`.

## Examples

```bash
bash "$SKILL_DIR/scripts/synthesize.sh" -- "Hello, this is Sutando."
bash "$SKILL_DIR/scripts/synthesize.sh" --voice ash --out /tmp/intro.mp3 -- "Hi."
```

Default output path: `results/openai-tts-{epoch}.mp3`. Cost: ~$0.02 per 60s of narration.

## If Invoked As A Slash Command

If ARGUMENTS is empty, ask the user for the text. Otherwise:

```bash
bash "$SKILL_DIR/scripts/synthesize.sh" -- "$ARGUMENTS"
```