Benchmark · read on October 27, 2026
Text-to-speech models measured by Speko
45 of the 96 text-to-speech (TTS) models in this index are filed under Speko , led by Gradium TTS, Inworld Realtime TTS-2 Flash and Alibaba Qwen3 TTS Fast. Same order and same measures as the full ranking.
| Rank | Model | Speed tier | P95 | Speed (shorter is faster) | Median | Listener Elo | Price per 1M chars | Best for |
|---|---|---|---|---|---|---|---|---|
| 2 |  Gradium TTSGradium | Headroom | 104.3 ms | 53.7 ms | 1,174 | $36 to $57.8 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 3 |  Inworld Realtime TTS-2 FlashInworld | Headroom | 100.9 ms | 58.1 ms | 1,218 | $10.4 to $15 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 4 |  Alibaba Qwen3 TTS FastAlibaba (Qwen) | Headroom | 98.8 ms | 62.9 ms | Not rated | $10 | Voice agents | |
| 7 |  SpeechifyAI Simba 3.2Speechify | Fast enough | 161.1 ms | 104.3 ms | 1,249 | $6.6 to $10 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 8 |  Inworld Realtime TTS-2Inworld | Fast enough | 194.7 ms | 149.1 ms | 1,267 | $15 to $25 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 9 |  Palabra TTS v1Palabra | Fast enough | 214.3 ms | 105.1 ms | Not rated | $12 | Voice agents | |
| 11 |  ElevenLabs Eleven v4 TurboElevenLabs | Fast enough | 238.6 ms | 188.9 ms | 1,333 | $40 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 12 |  ElevenLabs Flash v2.5ElevenLabs | Fast enough | 255.1 ms | 191 ms | 1,076 | $40 to $50 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 13 |  Deepgram Flux TTSDeepgram | Fast enough | 267 ms | 197.7 ms | 1,052 | $45 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 14 |  Soniox TTS RT v1Soniox | Visible delay | 319 ms | 258.3 ms | Not rated | $13 to $14.1 | Not rated | |
| 15 |  Soniox TTS Real-Time v2Soniox | Visible delay | 324.7 ms | 264.4 ms | 1,180 | $13 to $14.81 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 17 |  Rime Mist v3Rime | Visible delay | 359.9 ms | 275.2 ms | Not rated | $30 | Not rated | |
| 18 |  Cartesia Sonic 3.6Cartesia | Visible delay | 374.4 ms | 285.8 ms | 1,292 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 19 |  Cartesia Sonic 3.5Cartesia | Visible delay | 390.5 ms | 279.3 ms | 1,190 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 21 |  Rime CodaRime | Visible delay | 428.1 ms | 317.5 ms | 1,054 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 22 | Out of Set Airy TTSOut of Set | Visible delay | 453.9 ms | 212.3 ms | Not rated | $3.67 | Not rated | |
| 23 |  SpaceXAI Grok TTSxAI | Visible delay | 473.9 ms | 329.8 ms | 1,155 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 24 |  Deepgram Aura 2Deepgram | Visible delay | 525.4 ms | 263 ms | Not rated | $30 | Not rated | |
| 25 |  Fish Audio S2.1 ProFish Audio | Visible delay | 533 ms | 328.1 ms | 1,184 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 27 |  Smallest.ai Lightning V3.1 Pro (Jul 2026)Smallest.ai | Visible delay | 703.3 ms | 360.5 ms | 1,169 | $19.5 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 32 (tie) |  ElevenLabs Eleven v4ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,333 | $80 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 33 |  Google Gemini 3.8 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,280 | $15 to $16.5 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  Google Gemini 3.8 Flash-Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,256 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 37 (tie) |  ElevenLabs Eleven v3 ConversationalElevenLabs | No tier | Not timed | Not timed | Not timed | 1,213 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 37 (tie) |  Google Gemini 3.1 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,212 | $18.3 to $33.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 42 (tie) | | No tier | Not timed | Not timed | Not timed | 1,174 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 44 (tie) | | No tier | Not timed | Not timed | Not timed | 1,153 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 46 (tie) | | No tier | Not timed | Not timed | Not timed | 1,126 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 46 (tie) | | No tier | Not timed | Not timed | Not timed | 1,120 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 52 (tie) |  ElevenLabs Multilingual v2ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 52 (tie) |  ElevenLabs Turbo v2.5ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 62 (tie) | | No tier | Not timed | Not timed | Not timed | 1,056 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 62 (tie) |  Cartesia Sonic 3Cartesia | No tier | Not timed | Not timed | Not timed | 1,054 | $49 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 66 (tie) | | No tier | Not timed | Not timed | Not timed | 1,036 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 66 (tie) |  Bland Speech v3Bland AI | No tier | Not timed | Not timed | Not timed | 1,033 | $40 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 71 |  Smallest.ai Lightning v3.1Smallest.ai | No tier | Not timed | Not timed | Not timed | 1,020 | $17.5 to $25 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 79 (tie) |  Alibaba Qwen3 TTS FlashAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 939 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| Unranked |  ElevenLabs Flash v2ElevenLabs | No tier | Not timed | Not timed | Not timed | Not rated | $50 | Not rated |
| Unranked |  ElevenLabs Turbo v2ElevenLabs | No tier | Not timed | Not timed | Not timed | Not rated | $50 | Not rated |
| Unranked |  Maya 2 NativeMaya Research | No tier | Not timed | Not timed | Not timed | Not rated | $4 | Not rated |
| Unranked | | No tier | Not timed | Not timed | Not timed | Not rated | $13 | Not rated |
| Unranked |  Nari Qwen3-TTSAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | Not rated | $5 | Not rated |
| Unranked |  OpenAI GPT-4o mini TTSOpenAI | No tier | Not timed | Not timed | Not timed | Not rated | $20 | Not rated |
| Unranked | Paxa TTS Flash v1Paxa | No tier | Not timed | Not timed | Not timed | Not rated | $10 | Not rated |
| Unranked |  Rime arcanav3Rime | No tier | Not timed | Not timed | Not timed | Not rated | $40 | Not rated |
A model is filed under a benchmark when that benchmark measures it. Some model names are matched by inference; the methodology page lists them.
Frequently asked questions
- Which Speko TTS model is the fastest?
- Gradium TTS, with a P95 time to first audio of 104.3 ms in Coval's 30-day window. Of the 45 models on this page, 20 are timed.
- How are these models ordered?
- As in the full ranking: speed tier, then P95 time to first audio, with ties within 10 ms ordered by median time to first audio. Models Coval does not time follow, ordered by listener Elo; models with neither measure come last, in alphabetical order.