Unreal Speech

Unreal Speech: Fast and Affordable Text-to-Speech API

Unreal Speech offers a fast and affordable Text-to-Speech API solution that is significantly cheaper than alternatives like Eleven Labs. It allows users to stream audio quickly, request long-form audio, and provides per-word timestamps for enhanced control and synchronization.

What is Unreal Speech?

Unreal Speech is a text-to-speech API designed for developers and businesses seeking a cost-effective and high-performance solution for converting text into natural-sounding speech. It aims to provide a seamless experience for generating audio content, from short snippets to long-form audio files.

How does Unreal Speech work?

Unreal Speech utilizes advanced speech synthesis models to transform written text into spoken audio. The API offers several key features:

• Low Latency: Streams audio in as little as 300ms, making it suitable for real-time applications.
• High Capacity: Can handle requests for up to 10 hours of audio.
• Per-Word Timestamps: Provides precise timing information for each word, enabling synchronized highlighting and animation.
• Multiple Voices and Languages: Offers a variety of voices across different languages, including US English, UK English, Mandarin Chinese, Hindi, Spanish, Portuguese, Japanese, French, and Italian.
• Flexible Output Formats: Supports standard audio formats like MP3 and PCM µ-law, catering to different use cases.

Key Features of Unreal Speech

• Affordable Pricing: Unreal Speech is positioned as an economical alternative to other text-to-speech services, costing 11x less than Eleven Labs.
• Real-time Streaming: The /stream endpoint allows for quick conversion of up to 1,000 characters, delivering near-instantaneous audio.
• Asynchronous Synthesis: The /synthesisTasks endpoint is designed for creating longer audio files, with the ability to generate 10-hour audio in approximately 15 minutes.
• Timestamp Support: The API can provide timestamps at the word or sentence level, facilitating synchronized text highlighting.

How to use Unreal Speech?

To use Unreal Speech, you need an API key. Here’s how to get started:

1. Obtain an API Key: Sign up for a free API key on the Unreal Speech website.
2. Choose an Endpoint: Select the appropriate endpoint based on your needs:
   • /stream: For real-time streaming of short text.
   • /synthesisTasks: For generating longer audio files asynchronously.
   • /streamWithTimestamps: For streaming audio with word-level timestamps.
3. Make API Requests: Use the provided code samples (Python, Node.js, React Native, Bash) to integrate the API into your application.

Here's an example of using the /stream endpoint in Python:

import requests

response = requests.post(
  'https://api.v8.unrealspeech.com/stream',
  headers = {
    'Authorization' : 'Bearer YOUR_API_KEY'
  },
  json = {
    'Text': '''<YOUR_TEXT>''', # Up to 1,000 characters
    'VoiceId': '<VOICE_ID>', # af, af_bella, af_sarah, am_adam, am_michael, bf_emma, bf_isabella, bm_george, bm_lewis, af_nicole, af_sky
    'Bitrate': '192k', # 320k, 256k, 192k, ...
    'Speed': '0', # -1.0 to 1.0
    'Pitch': '1', # 0.5 to 1.5
    'Codec': 'libmp3lame', # libmp3lame or pcm_mulaw
  }
)

with open('audio.mp3', 'wb') as f:
    f.write(response.content)

Why choose Unreal Speech?

• Cost Savings: Significant reduction in text-to-speech costs compared to other providers.
• High Quality: Delivers natural-sounding speech with various voice options.
• Scalability: Capable of handling high volumes of requests, as evidenced by customer testimonials.
• Flexibility: Offers multiple API endpoints and output formats to suit different use cases.

Who is Unreal Speech for?

Unreal Speech is suitable for a wide range of users, including:

• Developers: Integrating text-to-speech functionality into applications.
• Content Creators: Generating audio versions of articles, blog posts, and other written content.
• Businesses: Automating customer service with voice assistants and chatbots.
• Educational Institutions: Creating accessible learning materials with audio support.

Unreal Speech Pricing

Unreal Speech offers different pricing plans to accommodate various needs:

• Free Plan: Includes a limited number of characters per month.
• Paid Plans: Offer larger character allowances and additional features.
• Enterprise Plan: Provides custom solutions and dedicated support for high-volume users.

Additional usage beyond the monthly allowance is charged per 1M characters, with rates varying based on the subscription plan.

Customer Testimonial

Derek Pankaew, CEO of Listening.com, shares his experience with Unreal Speech:

"Unreal Speech saved us 75% on our text-to-speech cost. It sounds better than Amazon Polly, and is much cheaper. We switched over at high volumes, and often processing 10,000+ pages per hour. Unreal was able to handle the volume, while delivering a high quality listening experience."

FAQ

• Do you offer voices in other languages? Yes, Unreal Speech provides 48 voices across 8 different languages.
• Can I create custom voices (voice cloning)? Not right now, but they're working on it!
• Can I use generated audio commercially? Yes, audio generated with Unreal Speech can be used commercially. Attribution is required for the free plan.

Unreal Speech is a compelling option for anyone seeking a fast, affordable, and reliable text-to-speech API. With its low latency, high capacity, and per-word timestamps, it's well-suited for a variety of applications and use cases.