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
Murf AI Falcon 2 Murf AI · text-to-speech (TTS) API
Visible delay286 ms median and 613 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).
Murf AI Falcon 2 is a proprietary text-to-speech (TTS) API from Murf AI, measured by two independent benchmarks: Artificial Analysis and Coval.
Proprietary Knowledge sharing Assistants Entertainment Customer service Artificial Analysis Coval Murf AI 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
- 286 ms
- P95 time to first audio (slow turns)Coval, 30 days
- 613 ms
- Naturalness EloSpeko
- not rated
- Listener Elo (95% interval)Artificial Analysis
- 1,153 ±13
- Numbers and dates (0 to 1)Speko
- not rated
- List price per 1M charactersall sources
- $10
- Tagged multilingual by Coval
- Customer service (Artificial Analysis): 29th, Elo 1172 ±26
Data read October 22, 2026. No combined score: methodology
Gradium TTS vs Murf AI Falcon 2 Fastest TTS APIs, by speed tierSpeed
On Coval's 30-day window ending October 22, 2026 (3,374 runs from US East), Murf AI Falcon 2 starts speaking after 285.9 ms on a typical turn (median) and 613.2 ms on a slow turn (P95, the slowest one in twenty). That P95 is 26th lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. On the median it is a tie (gap under 10 ms) with Cartesia Sonic 3.5 and Cartesia Sonic 3.6.
Voice quality
In the Artificial Analysis Speech Arena it holds 1,153 ±13 Elo (95% interval), 28th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 29th, at 1,172 Elo.
Numbers and dates
Speko has not scored its pronunciation of numbers and dates.
Price
Coval lists $10 per 1M characters (since Aug 31, 2026). Artificial Analysis lists $10. List prices, as each source prints them.
Benchmark measurements
Latency and accuracy — Coval (30-day window)
- Mean TTFA
- 310.9 ms
- P50 / median time-to-first-audio (TTFA)
- 285.9 ms
- P90 TTFA
- 582 ms
- P95 TTFA
- 613.2 ms
- Latency consistency (standard deviation)
- 177.4 ms
- Leading silence
- 212.1 ms
- Time to first byte (network arrival)
- 98.8 ms
- Accuracy: word error rate (WER)
- 2%
- WER basis
- pooled
- Latency runs
- 3,374 runs
- Accuracy runs
- 3,372 runs
- Window
- 30d
- Coval snapshot
- 2026-10-22T14:00:19.256741Z
- Coval model ID
- falcon-2
- Coval model page
- benchmarks.coval.ai
- Tagged multilingual
- ✓
- Feature tags
- multilingual
- List price per 1M characters
- 10 USD
- Price listed since
- Aug 31, 2026
Artificial Analysis Speech Arena
- Customer service rank
- 29
- Customer service Elo
- 1,172
- Customer service Elo 95% interval (±)
- 26
- Speech Arena Elo (blind listener preference)
- 1,153
- Elo 95% interval (±)
- 13
- Arena rank
- 28
- Arena rank range
- 26-30
- Arena appearances
- 2,441
- Voices tested
- 8
- Price per 1M characters
- 10 USD
- Released
- Jul 2026
- Artificial Analysis model
- Falcon 2
- Artificial Analysis leaderboard
- artificialanalysis.ai
Price (all sources)
- Lowest list price per 1M characters
- 10 USD
- Highest list price per 1M characters
- 10 USD
Not collected
- Naturalness (Speko naturalness) — not measured by Speko (reading of 2026-10-22)
- Numbers and dates (Speko pronunciation score) — not measured by Speko (reading of 2026-10-22)
Similar TTS models
Fish Audio S2.1 Pro
Visible delay Proprietary · Fish Audio
568 ms P95
317.9 ms median
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.
Knowledge sharing Assistants Entertainment Customer service
+3
Smallest.ai Lightning V3.1 Pro (Jul 2026)
Visible delay Proprietary · Smallest.ai
691 ms P95
356.1 ms median
Smallest.ai Lightning V3.1 Pro (Jul 2026) is a proprietary text-to-speech (TTS) API from Smallest.ai, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Knowledge sharing Assistants Entertainment Customer service
+3