Text-to-speech voices ranked for English narration
Compare provider-voice speech rankings and use a local English script to check names, pacing and pronunciation.

👁 112 reads
The public address line reads “The Worcester train is boarding.” A voice can sound natural for most of the sentence and still send a Massachusetts commuter searching for the wrong platform. I would shortlist candidates by listening preference and then keep this line in the audition.
What the board measures
Eleven v4 Turbo leads the provider-voice table. Voice selection is part of the result. A vendor can field a particularly suitable voice here; if a client has already approved a narrator, the controlled-voice track poses a closer question. Keep the model variant and the chosen voice in your estimate.
The November 17, 2026 snapshot
The table covers the top 25 and additional recently added entries captured in the source. Prices are the evaluator’s reported USD benchmark estimates. A blank price means the evaluator did not supply one.
| Rank and model | Elo and votes | Benchmark price |
|---|---|---|
| 1. Eleven v4 Turbo | 1340 (2,559 votes) | $40.00 /1M chars |
| 2. Eleven v4 | 1338 (2,853 votes) | $80.00 /1M chars |
| 3. Qwen-Audio-3.1-TTS-Plus | 1298 (2,614 votes) | $19.31 /1M chars |
| 4. Sonic 3.6 | 1295 (3,499 votes) | $49.00 /1M chars |
| 5. Simba 3.5 | 1291 (1,852 votes) | $6.58 /1M chars |
| 6. Gemini 3.8 Flash TTS | 1283 (3,772 votes) | $16.49 /1M chars |
| 7. Fish Audio Drama 3 | 1279 (1,861 votes) | $15.00 /1M chars |
| 8. Lightning V3.1 Pro (Oct 2026) | 1271 (2,173 votes) | $19.50 /1M chars |
| 9. Realtime TTS-2 | 1270 (2,884 votes) | $20.83 /1M chars |
| 10. Qwen-Audio-3.0-TTS-Plus | 1263 (3,173 votes) | $19.31 /1M chars |
| 11. Gemini 3.8 Flash-Lite TTS | 1259 (3,741 votes) | $11.03 /1M chars |
| 12. Simba 3.2 | 1250 (4,044 votes) | $6.58 /1M chars |
| 13. Fish Audio Drama 3 Preview | 1236 (2,882 votes) | $15.00 /1M chars |
| 14. Breeze TTS 2 | 1229 (3,006 votes) | $34.00 /1M chars |
| 15. v3 Conversational | 1216 (3,445 votes) | $50.00 /1M chars |
| 16. StepAudio 2.5 TTS (Aug 2026) | 1215 (2,893 votes) | $85.00 /1M chars |
| 17. Gemini 3.1 Flash TTS | 1215 (4,879 votes) | $18.31 /1M chars |
| 18. Realtime TTS-2 Flash | 1215 (3,323 votes) | $10.42 /1M chars |
| 19. Voxtral 3 TTS | 1213 (2,340 votes) | $13.00 /1M chars |
| 20. AssemblyAI-TTS-1 | 1212 (1,947 votes) | $15.00 /1M chars |
| 21. Luna TTS | 1196 (4,120 votes) | $15.00 /1M chars |
| 22. Sonic 3.5 | 1195 (4,387 votes) | $49.00 /1M chars |
| 23. Eleven v3 | 1190 (5,607 votes) | $100.00 /1M chars |
| 24. Ming-3.0-tts | 1182 (2,712 votes) | N/A |
| 25. Fish Audio S2.1 Pro (Oct 2026) | 1181 (2,711 votes) | $15.00 /1M chars |
Reading the result
Preference and cost. The score comes from the listening or viewing comparison. The price column describes a separate estimate. For a working budget I would record actual spend across all attempts and divide by the number of accepted deliverables.
For the next step, see the Quantslant ElevenLabs guide.
Changes since the October archive
The October 13 crawl contains 97 entries on this track. The November 17 board contains 105. The following labels occur only in the later capture. This comparison does not establish the exact release day or rule out a renamed entry.
- AssemblyAI-TTS-1
- Coda v2
- Falcon 2.1
- Fish Audio Drama 3
- Gradium TTS (Oct 2026)
- Lightning V3.1 Pro (Oct 2026)
- Ming-3.0-tts
- Phonon 31M (English)
- Simba 3.5
- Voxtral 3 TTS
Sources
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (accessed November 17, 2026)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice?tab=Leaderboard (accessed November 17, 2026)
More on this from QUANTSLANT
ai tools·Tencent HunyuanVideo and the memory bill for a shotUnderstand HunyuanVideo’s published memory requirements and compare a local run with renting a suitable GPU for a US project.