AnyToSpeech Premium and Characters
This is our own product
These are AnyToSpeech's Premium and Character voices, called the way the site calls them: the text goes through our pipeline, which splits long text at sentence ends and joins the pieces, adds number-reading hints, detects the language and retries failed pieces. The voice model underneath is Inworld TTS-2. Measured by us with the same harness and rules as every other row, with nothing tuned for the test.
Profile
Each spoke is one test, 0 at the centre and 100 at the edge.
Test by test
The dot shows where this model sits among all 19: left is last, right is first.
Long text
One document sent at five lengths, a single request each. Longest clean read: 15,000 characters.
| 1,000 characters | 2,000 characters | 4,000 characters | 8,000 characters | 15,000 characters |
|---|---|---|---|---|
| 100 | 100 | 100 | 100 | 100 |
Numbers, dates and symbols
59 of 60 sentences read correctly. Hover a square for the sentence.
Emotion control
24 of 40 directed clips measurably changed. Control used: text instruction.
Other languages
Audio from the test
Unedited clips exactly as the model returned them.
Compare with
Think a score is wrong? Check it.
Every test item, scoring rule and known limit is published, and the audio behind each number is on the page.