openai-tts

Text-to-speech via OpenAI Audio Speech API.

⭐2stars🔀0forks📁View on GitHub🕐Updated Jan 8, 2026

When & Why to Use This Skill

This Claude skill provides a powerful integration with the OpenAI Text-to-Speech (TTS) API, enabling the instant conversion of text into high-quality, lifelike spoken audio. It supports multiple AI voice personas and various output formats, making it an essential tool for creators and developers looking to add professional-grade narration and auditory dimensions to their projects.

Use Cases

  • Voiceover Production: Generate professional-grade narrations for videos, social media content, and marketing presentations using diverse voice profiles like 'Nova' or 'Onyx'.
  • Accessibility Enhancement: Transform written articles, documents, or messages into audio format to assist users with visual impairments or to facilitate hands-free content consumption.
  • E-Learning and Education: Create clear pronunciation guides and audio-based study materials to enhance language learning and educational engagement.
  • Automated Audio Notifications: Integrate speech synthesis into scripts or applications to provide audible status updates and real-time alerts.
nameopenai-tts
descriptionText-to-speech via OpenAI Audio Speech API.
homepagehttps://platform.openai.com/docs/guides/text-to-speech
metadata{"clawdbot":{"emoji":"🔊","requires":{"bins":["curl"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}}

OpenAI TTS (curl)

Generate speech from text via OpenAI's /v1/audio/speech endpoint.

Quick start

{baseDir}/scripts/speak.sh "Hello, world!"
{baseDir}/scripts/speak.sh "Hello, world!" --out /tmp/hello.mp3

Defaults:

  • Model: tts-1 (fast) or tts-1-hd (quality)
  • Voice: alloy (neutral), also: echo, fable, onyx, nova, shimmer
  • Format: mp3

Voices

Voice Description
alloy Neutral, balanced
echo Male, warm
fable British, expressive
onyx Deep, authoritative
nova Female, friendly
shimmer Female, soft

Flags

{baseDir}/scripts/speak.sh "Text" --voice nova --model tts-1-hd --out speech.mp3
{baseDir}/scripts/speak.sh "Text" --format opus --speed 1.2

Options:

  • --voice <name>: alloy|echo|fable|onyx|nova|shimmer (default: alloy)
  • --model <name>: tts-1|tts-1-hd (default: tts-1)
  • --format <fmt>: mp3|opus|aac|flac|wav|pcm (default: mp3)
  • --speed <n>: 0.25-4.0 (default: 1.0)
  • --out <path>: output file (default: stdout or auto-named)

API key

Set OPENAI_API_KEY, or configure in ~/.clawdbot/clawdbot.json:

{
  skills: {
    entries: {
      "openai-tts": {
        apiKey: "sk-..."
      }
    }
  }
}

Pricing

  • tts-1: ~$0.015 per 1K characters
  • tts-1-hd: ~$0.030 per 1K characters

Very affordable for short responses!