Unreal Speech
Transform text into lifelike, customizable voiceovers.
At a glance
Price not confirmed · Source review 2026-11-02- Price & billing
首页观察、未独立核验、购买前请复核官网：the observed homepage states no plan prices.
- Free allowance
Not separately confirmed. Check the current plan before relying on a free allowance.
- Best suited to
Streaming text-to-speech via API with word-level timestamp support.
Fit is editorial guidance, not a measured result.- Platforms
Access: not separately verified. Operating systems not separately verified.
Published-source facts and editorial guidance. No product test is implied. Confirm current conditions before purchase.
No product screenshot is claimed for this listing. Use the official website ↗ to inspect the current interface.
What to know before choosing
Good fit
Streaming text-to-speech via API with word-level timestamp support.
Limits and trade-offs
No prices are stated on the observed homepage; /stream caps at 1,000 characters per request.
Plans and free allowances
首页观察、未独立核验、购买前请复核官网：the observed homepage states no plan prices.
Evidence
Official Unreal Speech homepage and API samples ↗ (reviewed 2026-11-02)
Official published page review; no authenticated product test
Dates: Last reviewed 2026-11-02. Last reviewed is the latest source or editorial review date; it is not a content-change date.
A closer look at Unreal Speech
Unreal Speech is a text-to-speech API that streams audio from text, with a synchronous instant endpoint and a timestamped streaming endpoint for word-by-word highlighting.
Editorial guidance based on published documentation. The workflow below is a suggested starting point, not a measured product result.
When to choose Unreal Speech
- A developer wants instant text-to-speech with a synchronous response in about 0.3 seconds for up to 1,000 characters.
- A developer needs real-time word-level timestamps for word-by-word highlighting.
- A builder wants voice, speed, pitch, bitrate and codec controls in the API request.
When to choose something else
- A non-developer wanting a no-code voice tool will find only API code samples on the observed homepage.
- Developers who need a single /stream request to handle more than 1,000 characters, since the /stream endpoint takes text of up to 1,000 characters.
A practical starting workflow
- Send a POST request to the /stream endpoint with text of up to 1,000 characters, a VoiceId, bitrate, speed, pitch and codec.
- Receive streamed raw audio data synchronously with an instant response, and save it as an audio file.
- For highlighting, connect to the /streamWithTimestamps websocket with text, VoiceId, model, codec, sample rate and timestamp type word.
- Collect audio chunks and timestamp messages as they arrive, closing on the complete message.
Check before committing
- The observed homepage states no plan prices, so cost must be confirmed before integration.
- The /stream sample caps text at 1,000 characters per request, so longer text needs splitting.
- This entry describes published API samples and does not compare voice quality through testing.
Common questions
What does the /stream endpoint do?
It converts up to 1,000 characters as soon as possible, with a synchronous instant response in 0.3 seconds, streaming back raw audio data with no timestamps.
What does /streamWithTimestamps add?
It converts text with real-time word-level timestamps, streaming audio with precise word timing information, perfect for word-by-word highlighting.
What controls can I set?
VoiceId, bitrate such as 192k, speed from -1.0 to 1.0, pitch from 0.5 to 1.5, and codec such as libmp3lame or pcm_mulaw.
Compare approaches for this task
- ElevenLabs — Drafting narration or dialogue, then adjusting voice and delivery across selected passages.
- Typecast API — Adding expressive, low-latency AI voices to apps, agents and content via API.
Sources and checks
Last source review is not a date of product testing. No rating or test result is implied by inclusion. Check the current plan and terms before buying.