v2.12.0

New Feature Update: Text-to-Speech (TTS) Now Powered by GPT-4o-mini

Hello Straico Community!

We’re excited to announce a major upgrade to our Text-to-Speech (TTS) experience in Straico now powered by gpt-4o-mini-tts, bringing you more expressive voices and full control over how your text sounds.

What’s New:

New Model: gpt-4o-mini-tts

The TTS module now uses OpenAI’s cutting-edge gpt-4o-mini-tts model, delivering:

  • Faster and more natural voice generation.
  • Smarter pronunciation and intonation.
  • Customizable voice behavior through the new instructions parameter.

New Parameter: instructions

You can now personalize the tone, mood, and delivery style of the voice using natural instructions such as:

  • “Speak like a friendly podcast host.”
  • “Use a calm, reassuring tone.”
  • “Sound dramatic, like a movie trailer narrator.”
  • “Read this quickly and energetically.”
    This unlocks a whole new level of creative control over how your content is experienced.

Voice Updates: What’s New?

We’ve expanded our voice options with four brand-new voices:

  • Ash – Energetic male voice
  • Ballad – Calm, poetic male voice
  • Coral – Cheerful, friendly female voice
  • Sage – Soft, calm female voice

Try it out today!

Explore the new voices, add your own style with custom instructions, and bring your content to life like never before. Available now in Straico version v2.12.0.

What’s Next?

ElevenLabs integration is already on our roadmap and will be prioritized in our upcoming development cycle. Stay tuned!

Here is an example:

Text: “Welcome to Straico’s community! Let’s build something amazing together.”

Instruction (EXCITED): Say this in a cheerful way, like you’re excited.

Instruction (BORED): Say this in a bored manner, as if you’re not really enjoying it.

Ready to Revolutionize Your AI Experience?

Join our all-in-one AI platform and revolutionize your workflow. 
Tap into the power of advanced generative models for text, 
images, and audio—all in one place.