Aller au contenu

Google Gemini 3.8 Flash TTS Google · text-to-speech (TTS) API

1,010 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.

Google Gemini 3.8 Flash TTS is a proprietary text-to-speech (TTS) API from Google, 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
1642
Listener Elo (95% interval)Artificial Analysis
1,278 ±14
Numbers and dates (0 to 1)Speko
0.7
List price per 1M charactersall sources
$15 to $16.5
  • Customer service (Artificial Analysis): 3rd, Elo 1345 ±30

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

Gradium TTS vs Google Gemini 3.8 Flash TTS Fastest TTS APIs, by speed tier

Speed

Speko's board plots it at 1,010 ms time to first audio from US East; its model page reports a 1,031 ms sweep.

Voice quality

Speko rates its naturalness at 1,642 Elo from blind A/B votes on phone-agent lines (3rd highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,278 ±14 Elo (95% interval), 5th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 3rd, at 1,345 Elo.

Numbers and dates

Speko's pronunciation test on numbers, dates and currency scores it 0.7 on a 0-to-1 scale (4th 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 $16.5. Speko lists about $15. List prices, as each source prints them: a range of $15 to $16.5.

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
1,031 ms
Naturalness (Elo)
1,642
Pronunciation robustness (0 to 1)
0.7
Price per 1M characters
15 USD
Measured on
2026-09-24
Speko model
gemini-3.8-flash-tts
Speko model page
benchmarks.speko.ai
Time to first audio, board chart
1,010 ms

Artificial Analysis Speech Arena

Customer service rank
3
Customer service Elo
1,345
Customer service Elo 95% interval (±)
30
Speech Arena Elo (blind listener preference)
1,278
Elo 95% interval (±)
14
Arena rank
5
Arena rank range
4-7
Arena appearances
3,033
Voices tested
8
Price per 1M characters
16.5 USD
Released
Sept 2026
Artificial Analysis model
Gemini 3.8 Flash TTS
Artificial Analysis leaderboard
artificialanalysis.ai

Price (all sources)

Lowest list price per 1M characters
15 USD
Highest list price per 1M characters
16.5 USD

Not collected

Similar TTS models