Coqui XTTS v2
Listed Open weights · Coqui
1.7
/100
Coqui XTTS v2 is an open-weights text-to-speech (TTS) API from Coqui, measured by one independent benchmark, Artificial Analysis.
Spanish German French Portuguese
+4
Microsoft VibeVoice 1.5B Microsoft · text-to-speech (TTS) API
ListedSpeech Arena Elo 955 on Artificial Analysis, latency not measured; ranked 109th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 1.6/100, ranked 109th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 1.6 of 20 points.
Microsoft VibeVoice 1.5B is an open-weights text-to-speech (TTS) API from Microsoft, measured by one independent benchmark, Artificial Analysis.
Overall score
1.6 /100
Score breakdown
- Real-time speed 0 /60
- Voice quality 1.6 /20
- Accuracy 0 /15
- Price 0 /5
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Microsoft VibeVoice 1.5B ranks 109th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 1.6/100.
Real-time latency
Neither Coval nor Speko measures Microsoft VibeVoice 1.5B'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), Microsoft VibeVoice 1.5B has an Elo of 955 (±14, 95% confidence) from 2,095 blind comparisons, 77th highest of the 92 models Artificial Analysis rates.
Price
No price is published by Artificial Analysis or Speko for this model; price counts 0 of 5.
Benchmark measurements
Artificial Analysis Speech Arena
- Speech Arena Elo (blind listener preference)
- 955
- Elo 95% interval (±)
- 14
- Arena rank
- 77
- Arena rank range
- 77-79
- Arena appearances
- 2,095
- Voices tested
- 2
- Released
- Aug 2025
- Artificial Analysis model
- VibeVoice 1.5B
- 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 (Artificial Analysis price per 1M characters) — listed by Artificial Analysis without this value (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
KugelAudio Kugel 3
Listed Proprietary · KugelAudio
1.2
/100
KugelAudio Kugel 3 is a proprietary text-to-speech (TTS) API from KugelAudio, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis
Rime Mist V2
Listed Proprietary · Rime
1.8
/100
Rime Mist V2 is a proprietary text-to-speech (TTS) API from Rime, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis