Use case · Assistants · read on October 27, 2026
Best text-to-speech for assistants: 69 TTS models ranked by speed
Personal and in-app assistants that answer by voice: short replies, frequent turns, a voice people accept to hear all day. Speed on short replies, then listener preference, then price per million characters, since assistants speak a lot.
Recommendation for assistants
Best for: voice assistants and conversational apps. On this page the shortest wait for the first sound belongs to Gradium TTS (104.3 ms at P95), then Inworld Realtime TTS-2 Flash. One question narrows the choice: does a person wait on the line for the answer? If so, stay in the Headroom and Fast enough tiers.
All 69 models, fastest first
Order applied: speed tier, then P95, ties within 10 ms ordered by median time to first audio; models Coval does not time follow, ordered by listener elo.
| Rank | Model | Speed tier | P95 | Speed (shorter is faster) | Median | Listener Elo | Price per 1M chars | Best for |
|---|---|---|---|---|---|---|---|---|
| 1 |  Gradium TTSGradium | Headroom | 104.3 ms | 53.7 ms | 1,174 | $36 to $57.8 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 2 |  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 | |
| 3 |  SpeechifyAI Simba 3.0Speechify | Fast enough | 149.4 ms | 100.5 ms | 1,116 | $6.6 to $10 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 4 |  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 | |
| 5 |  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 | |
| 6 |  Fish Audio Drama 3 PreviewFish Audio | Fast enough | 209.3 ms | 146 ms | 1,245 | $15 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 7 |  ElevenLabs Eleven v4 TurboElevenLabs | Fast enough | 238.6 ms | 188.9 ms | 1,333 | $40 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 8 |  ElevenLabs Flash v2.5ElevenLabs | Fast enough | 255.1 ms | 191 ms | 1,076 | $40 to $50 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 9 |  Deepgram Flux TTSDeepgram | Fast enough | 267 ms | 197.7 ms | 1,052 | $45 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 10 |  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 | |
| 11 |  Murf AI Falcon 2Murf AI | Visible delay | 363.5 ms | 171.3 ms | 1,154 | $10 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 12 |  Cartesia Sonic 3.6Cartesia | Visible delay | 374.4 ms | 285.8 ms | 1,292 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 13 |  Cartesia Sonic 3.5Cartesia | Visible delay | 390.5 ms | 279.3 ms | 1,190 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 14 |  Rime CodaRime | Visible delay | 428.1 ms | 317.5 ms | 1,054 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 15 |  SpaceXAI Grok TTSxAI | Visible delay | 473.9 ms | 329.8 ms | 1,155 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 16 |  Fish Audio S2.1 ProFish Audio | Visible delay | 533 ms | 328.1 ms | 1,184 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 17 |  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 | |
| 18 |  Google Chirp 3: HDGoogle | Visible delay | 917.2 ms | 534.1 ms | 1,061 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 19 (tie) |  ElevenLabs Eleven v4ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,333 | $80 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 19 (tie) |  Alibaba Qwen-Audio-3.1-TTS-PlusAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 1,306 | $19.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 20 |  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 |
| 21 (tie) |  Alibaba Qwen-Audio-3.0-TTS-PlusAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 1,269 | $19.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 21 (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 |
| 24 (tie) |  BreezeBlue Breeze TTS 2BreezeBlue | No tier | Not timed | Not timed | Not timed | 1,227 | $34 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 24 (tie) | | No tier | Not timed | Not timed | Not timed | 1,221 | $13 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 24 (tie) |  ElevenLabs Eleven v3 ConversationalElevenLabs | No tier | Not timed | Not timed | Not timed | 1,213 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 24 (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 |
| 24 (tie) |  StepFun StepAudio 2.5 TTS (Aug 2026)StepFun | No tier | Not timed | Not timed | Not timed | 1,212 | $85 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 29 (tie) |  ElevenLabs Eleven v3ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,184 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 29 (tie) | | No tier | Not timed | Not timed | Not timed | 1,174 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) | | No tier | Not timed | Not timed | Not timed | 1,153 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  Gradium TTS (Aug 2026)Gradium | No tier | Not timed | Not timed | Not timed | 1,151 | $47.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) | | No tier | Not timed | Not timed | Not timed | 1,142 | $22 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  async Flash v1.5Async | No tier | Not timed | Not timed | Not timed | 1,137 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  StepFun Step TTS 2 (Mar 2026)StepFun | No tier | Not timed | Not timed | Not timed | 1,135 | $40 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 32 |  async Pro v1.0Async | No tier | Not timed | Not timed | Not timed | 1,127 | $20.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 33 (tie) | | No tier | Not timed | Not timed | Not timed | 1,126 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 33 (tie) | | No tier | Not timed | Not timed | Not timed | 1,120 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 36 (tie) |  Fish Audio S2 ProFish Audio | No tier | Not timed | Not timed | Not timed | 1,108 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 36 (tie) | | No tier | Not timed | Not timed | Not timed | 1,108 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 36 (tie) |  OpenAI TTS-1 HDOpenAI | No tier | Not timed | Not timed | Not timed | 1,106 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) |  ElevenLabs Multilingual v2ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) |  ElevenLabs Turbo v2.5ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,093 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) | | No tier | Not timed | Not timed | Not timed | 1,089 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) | | No tier | Not timed | Not timed | Not timed | 1,088 | $16 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) |  OpenAI TTS-1OpenAI | No tier | Not timed | Not timed | Not timed | 1,088 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 (tie) |  Google Gemini 2.5 Flash Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,087 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 41 |  Fish Audio OpenAudio S1Fish Audio | No tier | Not timed | Not timed | Not timed | 1,084 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 42 |  OpenAI GPT-Realtime-2OpenAI | No tier | Not timed | Not timed | Not timed | 1,073 | $191.6 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 44 (tie) |  Google Gemini 2.5 Flash TTS (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,067 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 44 (tie) |  Maya 2 FlashMaya Research | No tier | Not timed | Not timed | Not timed | 1,065 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 48 |  Amazon Polly GenerativeAmazon | No tier | Not timed | Not timed | Not timed | 1,063 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 49 (tie) | | No tier | Not timed | Not timed | Not timed | 1,056 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 49 (tie) |  Cartesia Sonic 3Cartesia | No tier | Not timed | Not timed | Not timed | 1,054 | $49 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 50 (tie) |  async Flash v1.0Async | No tier | Not timed | Not timed | Not timed | 1,049 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 50 (tie) |  Maya Research Maya1Maya Research | No tier | Not timed | Not timed | Not timed | 1,048 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 50 (tie) |  Maya 2 GlobalMaya Research | No tier | Not timed | Not timed | Not timed | 1,047 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 50 (tie) |  Boson AI Higgs Audio V3 TTSBoson AI | No tier | Not timed | Not timed | Not timed | 1,045 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 51 |  Google Gemini 2.5 Pro (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,040 | $18.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 53 (tie) | | No tier | Not timed | Not timed | Not timed | 1,036 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 53 (tie) |  Bland Speech v3Bland AI | No tier | Not timed | Not timed | Not timed | 1,033 | $40 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 55 |  Amazon Polly Long-FormAmazon | No tier | Not timed | Not timed | Not timed | 1,029 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 58 |  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 |
| 64 (tie) |  Neuphonic TTSNeuphonic | No tier | Not timed | Not timed | Not timed | 940 | $20.8 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Alibaba Qwen3 TTS FlashAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 939 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Alibaba Qwen3 TTSAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 929 | $13.8 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  KugelAudio Kugel 3KugelAudio | No tier | Not timed | Not timed | Not timed | 924 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 68 |  Amazon Polly NeuralAmazon | No tier | Not timed | Not timed | Not timed | 894 | $16 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 69 |  Amazon Polly StandardAmazon | No tier | Not timed | Not timed | Not timed | 829 | $4 | Customer service, Assistants, Entertainment, Knowledge sharing |
The same models, as listeners rate them
Artificial Analysis lets people compare voices blind. The ten highest listener elo scores among these models, highest first, with the 95% interval of each score. Overlapping intervals mean the order is not settled.
| # | Model | Listener Elo | 95% interval | Speed tier | Price per 1M chars |
|---|---|---|---|---|---|
| 1 | ElevenLabs Eleven v4 TurboElevenLabs | 1,333 | ±16 | Fast enough | $40 |
| 2 | ElevenLabs Eleven v4ElevenLabs | 1,333 | ±16 | No tier | $80 |
| 3 | Alibaba Qwen-Audio-3.1-TTS-PlusAlibaba (Qwen) | 1,306 | ±15 | No tier | $19.3 |
| 4 | Cartesia Sonic 3.6Cartesia | 1,292 | ±14 | Visible delay | $39.2 to $50 |
| 5 | Google Gemini 3.8 Flash TTSGoogle | 1,280 | ±14 | No tier | $15 to $16.5 |
| 6 | Alibaba Qwen-Audio-3.0-TTS-PlusAlibaba (Qwen) | 1,269 | ±13 | No tier | $19.3 |
| 7 | Inworld Realtime TTS-2Inworld | 1,267 | ±14 | Fast enough | $15 to $25 |
| 8 | Google Gemini 3.8 Flash-Lite TTSGoogle | 1,256 | ±13 | No tier | $10 to $11 |
| 9 | SpeechifyAI Simba 3.2Speechify | 1,249 | ±12 | Fast enough | $6.6 to $10 |
| 10 | Fish Audio Drama 3 PreviewFish Audio | 1,245 | ±14 | Fast enough | $15 |
Frequently asked questions
- What is the best text-to-speech model for assistants?
- Ranked by speed, Gradium TTS comes first of 69 models with a P95 time to first audio of 104.3 ms, followed by Inworld Realtime TTS-2 Flash. Speed is the first filter; check the listener Elo and price columns before you choose.
- How are the 69 models ordered?
- By speed tier, then by P95 time to first audio from Coval's 30-day window. Two P95 values within 10 ms are a tie, ordered by median time to first audio. Models Coval does not time follow, ordered by listener elo from Artificial Analysis.
- Which models are fast enough for assistants?
- Gradium TTS and Inworld Realtime TTS-2 Flash are in the Headroom tier (P95 under 120 ms) on this page. 7 more are in the Fast enough tier, up to 293 ms.
- Does the price change the order?
- No. Price per million characters is shown in the table as each benchmark prints it, but it never moves a model up or down: speed, voice quality, accuracy and price are read side by side.