Eleven v4 Turbo tops TTS arena at half the price of v4
- Source
- x.com
- Date
ElevenLabs' Eleven v4 Turbo takes the #1 spot on the Artificial Analysis Provider Voice TTS Arena Leaderboard, ahead of Eleven v4 while costing half the price Eleven v4 Turbo is the faster, lower-cost sibling of Eleven v4 from @ElevenLabs, designed to deliver comparable speech quality with lower latency and cost. Key takeaways: ➤ Provider Voice: Eleven v4 Turbo has an Elo of 1,334 (+19/-19) across 1,645 appearances, placing it ahead of Eleven v4 at 1,321, Alibaba's Qwen-Audio-3.1-TTS-Plus at 1,292 and Cartesia's Sonic 3.6 at 1,278. It ranks #1 in Customer Service and Entertainment and #2 in Assistants and Knowledge Sharing. ➤ Controlled Voice: Eleven v4 Turbo ranks #2 with an Elo of 1,173 (+15/-15) across 1,745 appearances, behind Qwen-Audio-3.1-TTS-Plus at 1,181 and ahead of Eleven v4 at 1,160. It ranks #1 in Arabic, German, Hindi and English (UK). ➤ Pronunciation Robustness: Eleven v4 Turbo scores 90.1%, ranking #2 behind Eleven v4 at 91.7% and ahead of Gemini 3.8 Flash TTS at 89.5%. ➤ Pricing: Eleven v4 Turbo is priced at $40/1M characters, half the price of Eleven v4 at $80/1M characters, compared to Sonic 3.6 at $49/1M characters and Gemini 3.8 Flash TTS at $16.49/1M…
Context
ElevenLabs' Eleven v4 Turbo is first on Artificial Analysis's Provider Voice text-to-speech leaderboard, but its lead over the full Eleven v4 model is too small to call it the better-sounding voice. The board scores models with Elo ratings, which rise and fall with the results of head-to-head comparisons. In its October 6 post, Artificial Analysis gives Turbo 1,334 across 1,645 appearances, with a margin of plus or minus 19 points, against 1,321 for v4. A 13-point gap sits inside that margin, so on these figures the board does not clearly separate the two.
What the post does separate cleanly is cost and speed. Artificial Analysis describes Turbo as the faster, lower-cost sibling of v4, designed to sound about as good with lower latency and cost. It lists Turbo at $40 per million characters against $80 for v4, and measures it producing 96 characters per second of generation time against 84 for v4. On these figures, choosing Turbo over v4 halves the price without a measurable drop on the preference board. The quality ordering does not always favor Turbo: on Artificial Analysis's pronunciation robustness test, v4 scores 91.7 percent to Turbo's 90.1, and Google's Gemini 3.8 Flash TTS is close behind at 89.5 percent while costing $16.49 per million characters.
On the separate Controlled Voice board, Turbo is second at 1,173, behind Alibaba's Qwen-Audio-3.1-TTS-Plus at 1,181, an 8-point gap that is also inside Turbo's stated margin of 15. That board did not stay put for long. Three days later Artificial Analysis reported that HeyGen Voice had taken first place there, ahead of both Qwen and Turbo. All rankings here are Artificial Analysis's own figures as of each post, and the audio samples and further detail promised in the rest of the thread were not available for this explanation.
Checking sign-in…
Loading comments…






