• AiNews.com
  • Posts
  • ElevenLabs Unveils Text to Sound Effects API for Developers

ElevenLabs Unveils Text to Sound Effects API for Developers

Author

Alicia Shapiro
June 19, 2024 • Estimated Reading Time: 3 minutes

An image showcasing ElevenLabs' Text to Sound Effects API. The background features a dynamic interface with text converting into sound waves and audio outputs. In the foreground, developers are using laptops and tablets to integrate the API into various applications. Icons represent multiple languages and high-quality voices, highlighting ultra-low latency and contextual awareness. The design includes subtle ElevenLabs branding and symbols of innovation and technology

ElevenLabs Unveils Text to Sound Effects API for Developers

ElevenLabs has introduced its latest innovation: the Text to Sound Effects API. To demonstrate its capabilities, they have developed the first Video to Sounds Effects app, which is available for free and is fully open-source. You can watch the showcase on X here.

Text to Speech API

ElevenLabs' text-to-speech API converts text into audio across 29 languages and offers thousands of voices. Developers can integrate these realistic voices into their React apps, use the Python library, or follow the websockets guide to get started. Visit the Voice Lab to explore pre-made voices or clone your own, and the Voices Library to see user-generated voices.

API Features

  • High-Quality Voices: Thousands of voices in 29 languages, delivered at 128kbps.

  • Ultra-Low Latency: Achieve ~400ms audio generation times with the Turbo model.

  • Contextual Awareness: The API understands text nuances for appropriate intonation and resonance.

The Turbo v2 model supports up to 30k characters (~30 minutes of audio) per request, while other models support up to 10k characters (~10 minutes of audio). The concurrency limit varies by subscription tier:

  • Free: 2 concurrent requests

  • Starter: 3 concurrent requests

  • Creator: 5 concurrent requests

  • Pro: 10 concurrent requests

  • Scale: 15 concurrent requests

For higher limits, users can contact the Enterprise team to discuss custom plans.

Supported Languages

The multilingual TTS API currently supports the following languages:

Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Russian, Danish, Bulgarian, Malay, Slovak, Croatian, Classic Arabic, Tamil, English, Polish, German, Spanish, French, Italian, Hindi, and Portuguese.

To use these languages, simply provide the input text in the desired language.

Learn More

Explore more about the API features and how to use the Text to Sound Effects API through the following links:

By launching the Text to Sound Effects API, ElevenLabs continues to support developers in creating dynamic audio experiences, enhancing the way we interact with text and sound in various applications.