Inworld · Proprietary · Read 2026-10-27
Inworld Realtime TTS-2 Flash: latency, voice quality, price and languages
- Rank
- 1 (tied) / 23
- Speed tier
- Headroom
- P95
- 100.9 ms
- Price / 1M chars
- $10.40 to $15
Inworld Realtime TTS-2 Flash is a proprietary text-to-speech model from Inworld. Coval measures a median of 58.1 ms and a P95 of 100.9 ms to first audio, which puts it in the Headroom speed tier, rank 1 (tied) of 23 in the multilingual ranking. Artificial Analysis or Speko tested it in 9 languages.
This summary is generated from the measures below; it is not a vendor description. Measures a source does not hold are shown as n/a and are never estimated.
Speed (Coval, 30 days, US East, English)
| Speed tier | Headroom |
| Median time to first audio | 58.1 ms |
| P90 | 83.7 ms |
| P95 | 100.9 ms |
| Mean | 81.1 ms |
| Standard deviation | 874.1 ms |
| Calls in the window | 2,612 |
| Cekura median, streamed text | 45 ms |
| Cekura median, full text | 46 ms |
Voice quality (never added together)
| Listener Elo (Artificial Analysis) | 1,218 ±13 |
| Customer-service Elo (Artificial Analysis) | 1,244 ±25 |
| Naturalness (Speko) | 1,501 |
| Naturalness estimate (Cekura, 1 to 5) | 4.46 |
Accuracy
| Reading accuracy (Cekura) | 93.2% |
| Numbers (Cekura) | 93% |
| Codes (Cekura) | 86% |
| Context (Cekura) | 98% |
| Medical terms (Cekura) | 99% |
| Hard passages judged correct (Artificial Analysis) | 77.8% |
| Numbers and dates (Speko score) | 0.58 |
| Word error rate (Coval) | 1.7% |
Price per 1 million characters
| Range across sources | $10.40 to $15 |
| Artificial Analysis | $10.40 |
| Speko | $15 |
| Coval | $15 |
| Cekura | $15 |
Coverage
| Access | Proprietary |
| Streaming | Measured |
| Coval tags | emotion-control, multilingual, voice-cloning |
| Rated for | Knowledge sharing, Assistants, Entertainment, Customer service, Voice agents |
| Languages tested | Arabic, Chinese, French, German, Hindi, Japanese, Portuguese, Spanish, Vietnamese |
Not collected
Every measure of the database is filled for this model.
Sources
- https://artificialanalysis.ai/text-to-speech (read 2026-10-27)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read 2026-10-27)
- https://benchmarks.cekura.ai/text-to-speech (read 2026-10-27)
- https://benchmarks-api-6wxgp27p2a-ue.a.run.app/v1/results/aggregates?benchmark=TTS&window=30d&include_series=false (read 2026-10-27)
- https://benchmarks.speko.ai/tts/ (read 2026-10-27)
- Vendor site: https://inworld.ai/
Keep exploring
Frequently asked questions
- How fast is Inworld Realtime TTS-2 Flash?
- Coval measures a median time to first audio of 58.1 ms and a P95 of 100.9 ms for Inworld Realtime TTS-2 Flash, over 30 days from the US East in English (Headroom tier).
- How much does Inworld Realtime TTS-2 Flash cost?
- The benchmarks print a list price of $10.40 to $15 per million characters for Inworld Realtime TTS-2 Flash.
- Which languages was Inworld Realtime TTS-2 Flash tested in?
- Artificial Analysis or Speko tested Inworld Realtime TTS-2 Flash in Arabic, Chinese, French, German, Hindi, Japanese, Portuguese, Spanish, Vietnamese.