Unreal Speech

Fast & Affordable Text-to-Speech API

Freemium

Description

Unreal Speech provides a developer-focused text-to-speech (TTS) solution centered around a powerful and cost-effective API. It enables the conversion of text into natural-sounding speech with options for real-time streaming and handling large volumes of text. The service emphasizes speed, boasting low latency for streaming audio suitable for interactive applications, and affordability, positioning itself as a significantly cheaper alternative to other major TTS providers.

The API offers flexibility through multiple endpoints tailored for different needs: instant streaming for short texts, synchronous generation for medium texts with timestamps, asynchronous processing for long-form audio (up to 10 hours or 500,000 characters), and WebSocket streaming for real-time audio with precise word-level timestamps. It supports various voices across multiple languages and allows customization of audio output parameters like speed, pitch, and bitrate, catering to diverse application requirements from real-time interactions to large-scale audio content production.

Key Features

API Access: Provides multiple endpoints (/stream, /speech, /synthesisTasks, /streamWithTimestamps) for different TTS needs.
Low Latency Streaming: Streams audio in as low as 300ms via /stream and /streamWithTimestamps endpoints.
Cost-Effective: Marketed as significantly cheaper than competitors like Eleven Labs.
High Volume Synthesis: Supports generating up to 10 hours of audio or processing 500,000 characters asynchronously.
Per-Word Timestamps: Offers precise word or sentence-level timestamps delivered via JSON or WebSocket.
Multi-Language Support: Provides 48 voices across 8 languages (including English, Chinese, Hindi, Spanish, French, etc.).
Customizable Output: Allows control over voice speed, pitch, and bitrate.
Developer Focused: Includes code samples (Python, Node.js, React Native, cURL) and SDK support.
Scalable Pricing: Offers tiered plans with volume discounts and character rollover for paid tiers.

Use Cases

Developing real-time voice applications.
Generating audio versions of articles, blogs, or news.
Creating audiobooks or long-form narrative content.
Building accessibility tools requiring spoken output.
Implementing interactive voice response (IVR) systems.
Adding voiceovers to videos or presentations.
Powering applications requiring synchronized text highlighting.

Frequently Asked Questions

Do you offer voices in other languages?

Yes, we provide 48 voices across 8 different languages, including US English, UK English, Mandarin Chinese, Hindi, Spanish, Portuguese, Japanese, French and Italian.

Can I create custom voices (voice cloning)?

Not right now, but we're working on it!

What happens if I use all of my monthly characters?

Additional usage over the monthly allowance will be charged daily at the rate of your current plan (ranging from $8 to $16 per 1M characters depending on the plan).

What happens to unused characters at the end of the month?

On the Free plan, characters reset monthly. On Paid plans, unused characters roll over to the next billing cycle.

Can I use generated audio commercially?

Yes. The Free plan requires attribution to Unreal Speech with a link. Paid plans do not require attribution.