Polly

💡 Definition

Amazon Polly is a service that turns text into lifelike speech, allowing you to create applications that talk, and build entirely new categories of speech-enabled products.

🔑 Key Concepts

• Text-to-Speech (TTS): Converts written text into audio.
• Lifelike Voices: Offers dozens of lifelike voices across a variety of languages.
• Neural TTS: Uses deep learning to produce even more natural-sounding human speech.
• SSML Support: Supports Speech Synthesis Markup Language to control pronunciation, volume, and speed.

⚙️ How it Works

You send text to the Polly API. Polly returns an audio stream (MP3) of that text being spoken.

🎯 Use Cases

• Content Creation: Converting articles or blogs into podcasts.
• E-learning: Adding voice to educational content.
• Accessibility: Reading text for visually impaired users.
• Telephony: Interactive Voice Response (IVR) systems.

💰 Pricing Model

• Characters: Charged per million characters of text synthesized.

📝 Exam Tips (CLF-C02)

• Keyword: "Text to Speech", "Lifelike voice".
• The opposite of Transcribe.

---

See Also: * Transcribe * Lex