G
Guava Daytona TTS
Visible delay Open weights · Guava
594.8 ms P95
466.4 ms median
Guava Daytona TTS is an open-weights text-to-speech (TTS) API from Guava, measured by one independent benchmark, Coval.
Coval
Fish Audio S2.1 Pro Fish Audio · text-to-speech (TTS) API
Visible delay318 ms median and 568 ms P95 time to first audio on Coval (30 days to October 22, 2026): Visible delay speed tier.
Benchmark summary: Visible delay speed tier on Coval's P95 (the voice becomes a visible part of the delay).
Fish Audio S2.1 Pro is a proprietary text-to-speech (TTS) API from Fish Audio, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Proprietary Knowledge sharing Assistants Entertainment Customer service Artificial Analysis Coval Speko Fish Audio Visible delay
Speed tier
Visible delayP95 of 320 ms or more. The voice becomes a visible part of the delay.
- Median time to first audioCoval, 30 days
- 318 ms
- P95 time to first audio (slow turns)Coval, 30 days
- 568 ms
- Naturalness EloSpeko
- not rated
- Listener Elo (95% interval)Artificial Analysis
- 1,189 ±14
- Numbers and dates (0 to 1)Speko
- not rated
- List price per 1M charactersall sources
- $15
- Tagged multilingual by Coval
- Customer service (Artificial Analysis): 21st, Elo 1211 ±29
Data read October 22, 2026. No combined score: methodology
Gradium TTS vs Fish Audio S2.1 Pro Fastest TTS APIs, by speed tierSpeed
On Coval's 30-day window ending October 22, 2026 (3,376 runs from US East), Fish Audio S2.1 Pro starts speaking after 317.9 ms on a typical turn (median) and 568 ms on a slow turn (P95, the slowest one in twenty). That P95 is 24th lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. Speko's board plots it at 198 ms time to first audio from US East.
Voice quality
In the Artificial Analysis Speech Arena it holds 1,189 ±14 Elo (95% interval), 20th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 21st, at 1,211 Elo.
Numbers and dates
Speko has not scored its pronunciation of numbers and dates.
Price
Artificial Analysis lists $15. List prices, as each source prints them.
Benchmark measurements
Latency and accuracy — Coval (30-day window)
- Mean TTFA
- 349.7 ms
- P50 / median time-to-first-audio (TTFA)
- 317.9 ms
- P90 TTFA
- 430.3 ms
- P95 TTFA
- 568 ms
- Latency consistency (standard deviation)
- 115.1 ms
- Leading silence
- 15.3 ms
- Time to first byte (network arrival)
- 334.4 ms
- Accuracy: word error rate (WER)
- 1.8%
- WER basis
- pooled
- Latency runs
- 3,376 runs
- Accuracy runs
- 3,374 runs
- Window
- 30d
- Coval snapshot
- 2026-10-22T14:00:19.256741Z
- Coval model ID
- s2.1-pro
- Coval model page
- benchmarks.coval.ai
- Tagged multilingual
- ✓
- Feature tags
- emotion-control, multilingual, voice-cloning
Speko
- Speko model
- s2.1-pro
- Speko model page
- benchmarks.speko.ai
- Time to first audio, board chart
- 198 ms
Artificial Analysis Speech Arena
- Customer service rank
- 21
- Customer service Elo
- 1,211
- Customer service Elo 95% interval (±)
- 29
- Speech Arena Elo (blind listener preference)
- 1,189
- Elo 95% interval (±)
- 14
- Arena rank
- 20
- Arena rank range
- 18-23
- Arena appearances
- 2,065
- Voices tested
- 8
- Price per 1M characters
- 15 USD
- Released
- Oct 2026
- Artificial Analysis model
- Fish Audio S2.1 Pro (Oct 2026)
- Artificial Analysis leaderboard
- artificialanalysis.ai
Price (all sources)
- Lowest list price per 1M characters
- 15 USD
- Highest list price per 1M characters
- 15 USD
Not collected
- Naturalness (Speko naturalness) — listed by Speko without this value (reading of 2026-10-22)
- Numbers and dates (Speko pronunciation score) — listed by Speko without this value (reading of 2026-10-22)
Similar TTS models
Deepgram Aura 2
Visible delay Proprietary · Deepgram
526.2 ms P95
266.4 ms median
Deepgram Aura 2 is a proprietary text-to-speech (TTS) API from Deepgram, measured by two independent benchmarks: Coval and Speko.
Spanish German French Coval
+1
Murf AI Falcon 2
Visible delay Proprietary · Murf AI
613.2 ms P95
285.9 ms median
Murf AI Falcon 2 is a proprietary text-to-speech (TTS) API from Murf AI, measured by two independent benchmarks: Artificial Analysis and Coval.
Knowledge sharing Assistants Entertainment Customer service
+2