Data read October 27, 2026
Thai TTS APIs in 2026: 10 models tested in Thai
10 models were tested in Thai by Artificial Analysis or Speko. 5 of the 10 are in the multilingual speed ranking; the others are not tagged multilingual by Coval or are not measured by it. The fastest ranked model tested in Thai is Inworld Realtime TTS-2.
No public source publishes naturalness or accuracy for Thai on its own, and all latency is measured in English from the US East. The page therefore says who was tested in Thai, and how fast each model is in general.
How the rows are ordered. Ranked models first, in ranking order (speed tier, then P95, ties by median); the 5 models without a rank follow alphabetically.
| Rank | Model | Speed tier From the Coval P95 | P95 (ms) 1 turn in 20 is slower | Languages tested | Listener Elo Artificial Analysis, with 95% interval | Price per 1M characters List price; a range when sources differ |
|---|---|---|---|---|---|---|
| 6 |  Inworld Realtime TTS-2 | Fast enough | 194.7 | 12 | 1,267 ±14 | $15 to $25 |
| 10 = |  Soniox TTS Real-Time v2 | Visible delay | 324.7 | 10 | 1,180 ±11 | $13 to $14.81 |
| 15 |  Cartesia Sonic 3.5 | Visible delay | 390.5 | 15 | 1,190 ±11 | $39.20 to $50 |
| 18 |  SpaceXAI Grok TTS | Visible delay | 473.9 | 11 | 1,155 ±13 | $15 |
| 22 |  Google Chirp 3: HD | Visible delay | 917.2 | 5 | 1,061 ±12 | $30 |
| not ranked |  ElevenLabs Eleven v3 | n/a | n/a | 10 | 1,184 ±10 | $100 |
| not ranked |  Google Gemini 3.1 Flash TTS | n/a | n/a | 9 | 1,212 ±11 | $18.30 to $33.30 |
| not ranked | | n/a | n/a | 4 | 1,126 ±11 | $100 |
| not ranked |  OpenAI GPT-4o mini TTS | n/a | n/a | 9 | n/a | $20 |
| not ranked | Paxa TTS Flash v1 | n/a | n/a | 1 | n/a | $10 |
Frequently asked questions
- Which TTS APIs support Thai?
- 10 models were tested in Thai. Starting with the best-ranked, Inworld Realtime TTS-2, Soniox TTS Real-Time v2, Cartesia Sonic 3.5, and SpaceXAI Grok TTS. Being tested in a language is evidence of support, not a quality score.
- Is TTS latency measured in Thai?
- No. Coval measures latency in English from the US East, so the latency columns show how fast each model starts in general, not in Thai.
- Which Thai TTS API is fastest?
- Among models tested in Thai that are also ranked, Inworld Realtime TTS-2 is first, with a P95 of 194.7 ms.
- How many of the 10 models are ranked?
- 5 of the 10 are in the multilingual speed ranking; the others are not tagged multilingual by Coval or are not measured by it.