Best Provider Voice Text to Speech (TTS) Models

Compare quality, speed, and price of speech generation models with every model speaking its own native voices where available.

For further details, see our methodology page.

Quality

Provider Voice Arena Preference Elo

Arena Elo: average Elo rating of the model · Higher is better

Pronunciation Robustness

% of highlighted spans human reviewers judged as pronounced correctly · English · Higher is better

Pronunciation Robustness by Category

% of highlighted spans human reviewers judged as pronounced correctly · English · Higher is better

Pricing

Price

Price: USD per 1M characters of text · Lower is better

Latency

Time to First Audio

Average time to first audio across all requests and prompt lengths (milliseconds) · Lower is better

Latency data available for 22 of 26 selected models

Last 7 days: 6 measurement days: 18 models

Last 7 days: 1 measurement day: Eleven v4 Turbo, ElevenLabs and Eleven v4, ElevenLabs

Last 7 days: 2 measurement days: v3 Conversational, ElevenLabs and Eleven v3, ElevenLabs

Throughput

Characters Per Second

Characters processed per second: # of characters per second of generation time · Higher is better

Frequently Asked Questions