Use case · Customer service · read on October 27, 2026
Best text-to-speech for customer service: 70 TTS models ranked by speed
Support calls, contact centers and help lines: a caller who waits in silence hangs up, and a voice that stumbles on an order number loses trust. Speed first, then how listeners rate the voice on customer service lines, then how well it reads numbers, dates and codes.
Recommendation for customer service
Best for: contact centers and support lines. 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 70 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, customer service.
| Rank | Model | Speed tier | P95 | Speed (shorter is faster) | Median | Listener Elo, customer service | Price per 1M chars | Best for |
|---|---|---|---|---|---|---|---|---|
| 1 |  Gradium TTSGradium | Headroom | 104.3 ms | 53.7 ms | 1,241 | $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 | 1,244 | $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 | 1,130 | $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 | 1,255 | $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 | 1,311 | $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 | 1,296 | $15 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 7 |  ElevenLabs Eleven v4 TurboElevenLabs | Fast enough | 238.6 ms | 188.9 ms | 1,372 | $40 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 8 |  ElevenLabs Flash v2.5ElevenLabs | Fast enough | 255.1 ms | 191 ms | 1,089 | $40 to $50 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 9 |  Deepgram Flux TTSDeepgram | Fast enough | 267 ms | 197.7 ms | 1,140 | $45 | Customer service, Voice agents, Assistants, Entertainment, Knowledge sharing | |
| 10 |  Soniox TTS Real-Time v2Soniox | Visible delay | 324.7 ms | 264.4 ms | 1,213 | $13 to $14.81 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 11 |  Murf AI Falcon 2Murf AI | Visible delay | 363.5 ms | 171.3 ms | 1,179 | $10 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 12 |  Cartesia Sonic 3.6Cartesia | Visible delay | 374.4 ms | 285.8 ms | 1,331 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 13 |  Cartesia Sonic 3.5Cartesia | Visible delay | 390.5 ms | 279.3 ms | 1,203 | $39.2 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 14 |  Rime CodaRime | Visible delay | 428.1 ms | 317.5 ms | 1,108 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 15 |  SpaceXAI Grok TTSxAI | Visible delay | 473.9 ms | 329.8 ms | 1,193 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 16 |  Fish Audio S2.1 ProFish Audio | Visible delay | 533 ms | 328.1 ms | 1,213 | $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 | 1,189 | $19.5 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 18 |  Google Chirp 3: HDGoogle | Visible delay | 917.2 ms | 534.1 ms | 1,108 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing | |
| 19 (tie) |  ElevenLabs Eleven v4ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,374 | $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 | 1,349 | $19.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 19 (tie) |  Google Gemini 3.8 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,341 | $15 to $16.5 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 20 |  Google Gemini 3.8 Flash-Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,311 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 21 |  Alibaba Qwen-Audio-3.0-TTS-PlusAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 1,288 | $19.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 22 (tie) |  BreezeBlue Breeze TTS 2BreezeBlue | No tier | Not timed | Not timed | Not timed | 1,277 | $34 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 22 (tie) | | No tier | Not timed | Not timed | Not timed | 1,272 | $13 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 22 (tie) |  ElevenLabs Eleven v3 ConversationalElevenLabs | No tier | Not timed | Not timed | Not timed | 1,271 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 23 (tie) |  Google Gemini 3.1 Flash TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,244 | $18.3 to $33.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 23 (tie) |  StepFun StepAudio 2.5 TTS (Aug 2026)StepFun | No tier | Not timed | Not timed | Not timed | 1,243 | $85 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 26 |  ElevenLabs Eleven v3ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,219 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 27 |  Gradium TTS (Aug 2026)Gradium | No tier | Not timed | Not timed | Not timed | 1,209 | $47.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 29 (tie) | | No tier | Not timed | Not timed | Not timed | 1,178 | $22 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 29 (tie) | | No tier | Not timed | Not timed | Not timed | 1,173 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 30 | | No tier | Not timed | Not timed | Not timed | 1,172 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  StepFun Step TTS 2 (Mar 2026)StepFun | No tier | Not timed | Not timed | Not timed | 1,153 | $40 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  async Flash v1.5Async | No tier | Not timed | Not timed | Not timed | 1,152 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) | | No tier | Not timed | Not timed | Not timed | 1,146 | $16 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) | | No tier | Not timed | Not timed | Not timed | 1,145 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  async Pro v1.0Async | No tier | Not timed | Not timed | Not timed | 1,141 | $20.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  Fish Audio S2 ProFish Audio | No tier | Not timed | Not timed | Not timed | 1,140 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  Google Gemini 2.5 Flash TTS (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,139 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) | | No tier | Not timed | Not timed | Not timed | 1,137 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  OpenAI TTS-1 HDOpenAI | No tier | Not timed | Not timed | Not timed | 1,136 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 31 (tie) |  ElevenLabs Turbo v2.5ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,129 | $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 32 |  Maya 2 FlashMaya Research | No tier | Not timed | Not timed | Not timed | 1,125 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  ElevenLabs Multilingual v2ElevenLabs | No tier | Not timed | Not timed | Not timed | 1,123 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) | | No tier | Not timed | Not timed | Not timed | 1,121 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  OpenAI GPT-Realtime-2OpenAI | No tier | Not timed | Not timed | Not timed | 1,120 | $191.6 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) | | No tier | Not timed | Not timed | Not timed | 1,118 | $60 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  OpenAI TTS-1OpenAI | No tier | Not timed | Not timed | Not timed | 1,105 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 34 (tie) |  Cartesia Sonic 3Cartesia | No tier | Not timed | Not timed | Not timed | 1,104 | $49 to $50 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 35 |  Maya 2 GlobalMaya Research | No tier | Not timed | Not timed | Not timed | 1,100 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 38 (tie) |  Fish Audio OpenAudio S1Fish Audio | No tier | Not timed | Not timed | Not timed | 1,086 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 38 (tie) |  Google Gemini 2.5 Flash Lite TTSGoogle | No tier | Not timed | Not timed | Not timed | 1,085 | $9.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 39 | | No tier | Not timed | Not timed | Not timed | 1,085 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 41 |  Amazon Polly GenerativeAmazon | No tier | Not timed | Not timed | Not timed | 1,082 | $30 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 43 |  Boson AI Higgs Audio V3 TTSBoson AI | No tier | Not timed | Not timed | Not timed | 1,082 | $15 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 44 |  Maya Research Maya1Maya Research | No tier | Not timed | Not timed | Not timed | 1,069 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 47 (tie) | | No tier | Not timed | Not timed | Not timed | 1,068 | $87.5 to $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 47 (tie) |  Smallest.ai Lightning v3.1Smallest.ai | No tier | Not timed | Not timed | Not timed | 1,068 | $17.5 to $25 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 49 (tie) |  async Flash v1.0Async | No tier | Not timed | Not timed | Not timed | 1,059 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 49 (tie) |  Amazon Polly Long-FormAmazon | No tier | Not timed | Not timed | Not timed | 1,056 | $100 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 49 (tie) |  Google Gemini 2.5 Pro (Dec 2025)Google | No tier | Not timed | Not timed | Not timed | 1,047 | $18.3 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 51 |  Bland Speech v3Bland AI | No tier | Not timed | Not timed | Not timed | 1,050 | $40 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 63 |  KugelAudio Kugel 3KugelAudio | No tier | Not timed | Not timed | Not timed | 990 | Not collected | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Neuphonic TTSNeuphonic | No tier | Not timed | Not timed | Not timed | 968 | $20.8 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Amazon Polly NeuralAmazon | No tier | Not timed | Not timed | Not timed | 957 | $16 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Alibaba Qwen3 TTSAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 953 | $13.8 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Alibaba Qwen3 TTS FlashAlibaba (Qwen) | No tier | Not timed | Not timed | Not timed | 953 | $10 to $11 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 64 (tie) |  Rime Mist V2Rime | No tier | Not timed | Not timed | Not timed | 924 | $31.1 | Customer service, Knowledge sharing |
| 69 |  Amazon Polly StandardAmazon | No tier | Not timed | Not timed | Not timed | 854 | $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, customer service scores among these models, highest first, with the 95% interval of each score. Overlapping intervals mean the order is not settled.
| # | Model | Listener Elo, customer service | 95% interval | Speed tier | Price per 1M chars |
|---|---|---|---|---|---|
| 1 | ElevenLabs Eleven v4ElevenLabs | 1,374 | ±31 | No tier | $80 |
| 2 | ElevenLabs Eleven v4 TurboElevenLabs | 1,372 | ±33 | Fast enough | $40 |
| 3 | Alibaba Qwen-Audio-3.1-TTS-PlusAlibaba (Qwen) | 1,349 | ±30 | No tier | $19.3 |
| 4 | Google Gemini 3.8 Flash TTSGoogle | 1,341 | ±28 | No tier | $15 to $16.5 |
| 5 | Cartesia Sonic 3.6Cartesia | 1,331 | ±28 | Visible delay | $39.2 to $50 |
| 6 | Inworld Realtime TTS-2Inworld | 1,311 | ±28 | Fast enough | $15 to $25 |
| 7 | Google Gemini 3.8 Flash-Lite TTSGoogle | 1,311 | ±27 | No tier | $10 to $11 |
| 8 | Fish Audio Drama 3 PreviewFish Audio | 1,296 | ±30 | Fast enough | $15 |
| 9 | Alibaba Qwen-Audio-3.0-TTS-PlusAlibaba (Qwen) | 1,288 | ±27 | No tier | $19.3 |
| 10 | BreezeBlue Breeze TTS 2BreezeBlue | 1,277 | ±27 | No tier | $34 |
Frequently asked questions
- What is the best text-to-speech model for customer service?
- Ranked by speed, Gradium TTS comes first of 70 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 70 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, customer service from Artificial Analysis.
- Which models are fast enough for customer service?
- 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.