Try AnyToSpeech
Benchmark › Speech models › Inworld TTS-2
Inworld · tested 2026-11-22

Inworld TTS-2

84.8overall · rank 8 of 19 speech models
API model: inworld-tts-2 Reached through Inworld API Voice: Ashley48 kHz

Profile

Each spoke is one test, 0 at the centre and 100 at the edge.

Inworld TTS-2Median of all models (dashed)

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: 2,000 characters.

1,000 characters2,000 characters4,000 characters8,000 characters15,000 characters
100100rejectedrejectedrejected

Numbers, dates and symbols

60 of 60 sentences read correctly. Hover a square for the sentence.

Emotion control

24 of 40 directed clips measurably changed. Control used: text instruction.

Angry
5/10
Excited
9/10
Scared
10/10
Whisper
0/10

Other languages

Other misses

Repeated words

Text: Wait. Wait. Wait. Did you hear that? Wait.
Heard: Wait, wait, wait, wait, did you hear that? Wait!

Audio from the test

Unedited clips exactly as the model returned them.

Plain sentence
TextThe ferry leaves the harbor every morning just after sunrise, and most of the passengers are still half asleep.
Repetition
TextNo, no, no, no, no. I said no.
Repetition (most errors)
miss
TextWait. Wait. Wait. Did you hear that? Wait. HeardWait, wait, wait, wait, did you hear that? Wait!
Money amount
TextThe total comes to $1,250.50 after tax.
Spanish
Japanese
Neutral reading
Asked for: angry
Asked for: excited
Asked for: sad (not scored yet)
Asked for: whisper

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.

Read the methodology