Deepgram Flux TTS
Contender Proprietary · Deepgram
49.6
/100
Deepgram Flux TTS is a proprietary text-to-speech (TTS) API from Deepgram, measured by two independent benchmarks: Coval and Speko.
Coval Speko
Rime Coda Rime · text-to-speech (TTS) API
Contender294.2 ms P50 time-to-first-audio on Coval; ranked 14th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 47.1/100, ranked 14th of 112 in the TTS for Voice Agents 2026 index (Contender). Strongest criterion: real-time speed, 32.4 of 60 points.
Rime Coda is a proprietary text-to-speech (TTS) API from Rime, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Overall score
47.1 /100
Score breakdown
- Real-time speed 32.4 /60
- Voice quality 9.3 /20
- Accuracy 3.9 /15
- Price 1.5 /5
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Rime Coda ranks 14th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 47.1/100.
Real-time latency
On Coval's 30-day window ending October 1, 2026 (11,808 runs), Rime Coda has a P50 (median) time-to-first-audio (TTFA) of 294.2 ms, 17th lowest of the 31 models Coval measures. Its P99, the slowest 1% of turns, is 438.1 ms (15th lowest of the 31 models Coval measures). Latency consistency: a standard deviation of 46 ms (8th lowest of the 31 models Coval measures). Mean time to first byte (TTFB) is 180.3 ms.
Accuracy (word error rate)
Coval measures an accuracy (word error rate) of 4.9% over 11,788 samples on the same window, 15th lowest of the 31 models Coval measures.
Voice quality
In the Artificial Analysis Speech Arena (capture of October 1, 2026), Rime Coda has an Elo of 1,060 (±13, 95% confidence) from 2,216 blind comparisons, 53rd highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,535 Elo from blind A/B votes (21st highest of the 41 models Speko rates).
Price
Artificial Analysis lists Rime Coda at $50 per 1M characters (57th lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $50 per 1M characters.
Languages tested
Tested in Korean by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
Benchmark measurements
Latency and accuracy — Coval (30-day window)
- Mean TTFA
- 302.3 ms
- P50 / median time-to-first-audio (TTFA)
- 294.2 ms
- P90 TTFA
- 366 ms
- P95 TTFA
- 391.3 ms
- P99 TTFA (slowest turns)
- 438.1 ms
- Latency consistency (standard deviation)
- 46 ms
- Leading silence
- 122 ms
- Time to first byte (network arrival)
- 180.3 ms
- Accuracy: word error rate (WER)
- 4.9%
- WER basis
- per-clip mean
- Latency runs
- 11,808 runs
- Accuracy runs
- 11,788 runs
- Window
- 30d
- Coval snapshot
- 2026-10-01T10:11:47.318752Z
- Coval model ID
- coda
- Coval model page
- benchmarks.coval.ai
Speko
- Naturalness (Elo)
- 1,535
- Price per 1M characters
- 50 USD
- Measured on
- 2026-09-08
- Speko model
- coda
- Speko model page
- benchmarks.speko.ai
Artificial Analysis Speech Arena
- Speech Arena Elo (blind listener preference)
- 1,060
- Elo 95% interval (±)
- 13
- Arena rank
- 53
- Arena rank range
- 48-59
- Arena appearances
- 2,216
- Voices tested
- 7
- Price per 1M characters
- 50 USD
- Released
- May 2026
- Artificial Analysis model
- Coda
- Artificial Analysis leaderboard
- artificialanalysis.ai
Not collected
- Speed (Speko time to first audio) — listed by Speko without this value (capture of 2026-10-01); counts 0
- Accuracy (Speko robustness) — listed by Speko without this value (capture of 2026-10-01); counts 0
Similar TTS models
Fluxions vui
Contender Proprietary · Fluxions
47
/100
Fluxions vui is a proprietary text-to-speech (TTS) API from Fluxions, measured by one independent benchmark, Coval.
Voice agents Coval
SpeechifyAI Simba 3.2
Contender Proprietary · Speechify
51.6
/100
SpeechifyAI Simba 3.2 is a proprietary text-to-speech (TTS) API from Speechify, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.
Knowledge sharing Assistants Entertainment Customer service
+3