Kokoro 82M v1.0
Listed Open weights · Kokoro
7.1
/100
Kokoro 82M v1.0 is an open-weights text-to-speech (TTS) API from Kokoro, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis
Mistral Voxtral TTS Mistral · text-to-speech (TTS) API
ListedSpeech Arena Elo 1,079 on Artificial Analysis, latency not measured; ranked 61st (tied) of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 7.1/100, ranked 61st (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: price, 1.6 of 5 points.
Mistral Voxtral TTS is an open-weights text-to-speech (TTS) API from Mistral, measured by one independent benchmark, Artificial Analysis.
Overall score
7.1 /100
Score breakdown
- Real-time speed 0 /60
- Voice quality 5.5 /20
- Accuracy 0 /15
- Price 1.6 /5
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Mistral Voxtral TTS ranks 61st of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 7.1/100.
Real-time latency
Neither Coval nor Speko measures Mistral Voxtral TTS's latency, so it scores 0 of 60 on real-time speed and does not appear in the real-time ranking.
Accuracy (word error rate)
No accuracy measurement: Coval does not measure its word error rate and Speko does not rate its pronunciation robustness, so accuracy counts 0 of 15.
Voice quality
In the Artificial Analysis Speech Arena (capture of October 1, 2026), Mistral Voxtral TTS has an Elo of 1,079 (±13, 95% confidence) from 2,094 blind comparisons, 42nd highest of the 92 models Artificial Analysis rates.
Price
Artificial Analysis lists Mistral Voxtral TTS at $16 per 1M characters (28th lowest of the 78 models Artificial Analysis lists a price for).
Scoring note
Artificial Analysis changed its Speech Arena Elo between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (1,080, then 1,079): the score uses the average, 1,079.5. The value shown is the latest.
Languages tested
Tested in Spanish, German, French, Portuguese and Hindi by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
Benchmark measurements
Artificial Analysis Speech Arena
- Speech Arena Elo (blind listener preference)
- 1,079
- Elo 95% interval (±)
- 13
- Arena rank
- 42
- Arena rank range
- 37-48
- Arena appearances
- 2,094
- Voices tested
- 3
- Price per 1M characters
- 16 USD
- Released
- Mar 2026
- Artificial Analysis model
- Voxtral TTS
- Artificial Analysis leaderboard
- artificialanalysis.ai
Not collected
- Speed (Coval time to first audio) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Speed (Speko time to first audio) — not measured by Speko (capture of 2026-10-01); counts 0
- Quality (Speko naturalness) — not measured by Speko (capture of 2026-10-01); counts 0
- Accuracy (Coval word error rate) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Accuracy (Speko robustness) — not measured by Speko (capture of 2026-10-01); counts 0
- Price (Speko cost per 1M characters) — not measured by Speko (capture of 2026-10-01); counts 0
Similar TTS models
Resemble AI Chatterbox HD
Listed Proprietary · Resemble AI
7.3
/100
Resemble AI Chatterbox HD is a proprietary text-to-speech (TTS) API from Resemble AI, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis
MiniMax Speech-02-HD
Listed Proprietary · MiniMax
6.8
/100
MiniMax Speech-02-HD is a proprietary text-to-speech (TTS) API from MiniMax, measured by one independent benchmark, Artificial Analysis.
Entertainment Artificial Analysis