Aller au contenu

ElevenLabs Eleven v4 ElevenLabs · text-to-speech (TTS) API

852 ms time to first audio on Speko's board (read October 22, 2026); not measured by Coval, so no speed tier.

Benchmark summary: No speed tier: Coval, the source of the tiers, does not measure this model. On the Speko speed and naturalness frontier: no other model is both faster and rated higher.

ElevenLabs Eleven v4 is a proprietary text-to-speech (TTS) API from ElevenLabs, measured by two independent benchmarks: Artificial Analysis and Speko.

Speed tier

Not measured by Coval

No speed tier: Coval, the source of the tiers, does not measure this model.

Median time to first audioCoval, 30 days
—
P95 time to first audio (slow turns)Coval, 30 days
—
Naturalness EloSpeko
1708
Listener Elo (95% interval)Artificial Analysis
1,329 ±16
Numbers and dates (0 to 1)Speko
0.9
List price per 1M charactersall sources
$80

Data read October 22, 2026. No combined score: methodology

Gradium TTS vs ElevenLabs Eleven v4 Fastest TTS APIs, by speed tier

Speed

Speko's board plots it at 852 ms time to first audio from US East; its model page reports a 844 ms sweep.

Voice quality

Speko rates its naturalness at 1,708 Elo from blind A/B votes on phone-agent lines (the highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,329 ±16 Elo (95% interval), 2nd highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 2nd, at 1,369 Elo.

Numbers and dates

Speko's pronunciation test on numbers, dates and currency scores it 0.9 on a 0-to-1 scale (the highest of the 30 models Speko scores). This is the accuracy measure used here; Coval's word error rate separates models too little to compare them.

Price

Artificial Analysis lists $80. Speko lists about $80. List prices, as each source prints them.

Languages tested

Tested in Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi and Vietnamese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.

Benchmark measurements

Speko

P50 TTFA, US East
844 ms
Naturalness (Elo)
1,708
Pronunciation robustness (0 to 1)
0.9
Price per 1M characters
80 USD
Measured on
2026-09-28
Speko model
eleven_v4
Speko model page
benchmarks.speko.ai
Time to first audio, board chart
852 ms

Artificial Analysis Speech Arena

Customer service rank
2
Customer service Elo
1,369
Customer service Elo 95% interval (±)
33
Speech Arena Elo (blind listener preference)
1,329
Elo 95% interval (±)
16
Arena rank
2
Arena rank range
1-2
Arena appearances
2,346
Voices tested
8
Price per 1M characters
80 USD
Released
Sept 2026
Artificial Analysis model
Eleven v4
Artificial Analysis leaderboard
artificialanalysis.ai

Price (all sources)

Lowest list price per 1M characters
80 USD
Highest list price per 1M characters
80 USD

Frontiers

On the Speko speed and naturalness frontier
✓

Not collected

Similar TTS models