Inworld · read on October 27, 2026
Inworld Realtime TTS-2 Flash
Inworld Realtime TTS-2 Flash is a TTS (text-to-speech) model from Inworld. Coval measures its P95 time to first audio at 100.9 ms, which puts it in the Headroom speed tier. It ranks 3 of 86 in the full ranking.
- Speed tier
- Headroom
- P95 / median
- 100.9 ms / 58.1 ms
- Listener Elo
- 1,218
- Price per 1M chars
- $10.4 to $15
Where it ranks
Full ranking: 3 of 86. Use case ranks, by speed:
- Customer service: 2 of 70
- Voice agents: 3 of 13
- Assistants: 2 of 69
- Entertainment: 2 of 69
- Knowledge sharing: 2 of 73
The tier and the ranks are computed by this site from the benchmarks' figures, not declared by Inworld.
Measurements and sources
Coval
| Median time to first audio (P50) | 58.1 ms |
| Time to first audio, P95 | 100.9 ms |
| Time to first audio, mean | 81.1 ms |
| Time to first audio, P90 | 83.7 ms |
| Timed requests | 2,612 |
Speko
| Naturalness score | 1,501 |
| Latency, board chart | 50 ms |
| Latency, model page sweep (median) | 82 ms |
| Numbers and dates pronunciation | 0.58 |
Artificial Analysis
| Listener Elo | 1,218 |
| Listener Elo, 95% interval | 13 |
| Listener Elo, customer service | 1,244 |
| Hard passages pronounced correctly | 77.8% |
Cekura
| Time to first audio, streamed text | 45 ms |
| Time to first audio, text sent whole | 46 ms |
| Reading accuracy | 93.2% |
| Estimated naturalness (1 to 5) | 4.46 |
Details
| Provider | Inworld |
| Access | Proprietary |
| Streaming | A benchmark measures its time to first audio |
| Features listed by Coval | emotion-control, multilingual, voice-cloning |
| Languages tested | Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi, Vietnamese |
| Measured by | Artificial Analysis, Cekura, Coval, Speko |
| Official site | inworld.ai |
Sources
- https://artificialanalysis.ai/text-to-speech (read on October 27, 2026)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read on October 27, 2026)
- https://benchmarks.cekura.ai/text-to-speech (read on October 27, 2026)
- https://benchmarks-api-6wxgp27p2a-ue.a.run.app/v1/results/aggregates?benchmark=TTS&window=30d&include_series=false (read on October 27, 2026)
- https://benchmarks.speko.ai/tts/ (read on October 27, 2026)
Values are copied from these pages on the date shown. The match between this model and its benchmark entries is inferred, because a source writes the name differently: Cekura: “Inworld TTS-2 Flash”; Coval: “Inworld AI TTS Flash 2”; Speko: “Inworld tts 2 flash”. See the methodology.
Compare it with the reference model: Gradium TTS vs Inworld Realtime TTS-2 Flash.