language benchmark
Common Voice 15
Common Voice is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Version 15.0 contains 28,750 recorded hours across 114 languages, consisting of crowdsourced voice recordings with corresponding transcriptions.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Common Voice 15 Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 0.076 points | 100.0% | 1 | C |
Common Voice 15 Highlights
The leading models and scores on this benchmark.
What is Common Voice 15?
What Common Voice 15 measures and how its scores work.
Common Voice is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Version 15.0 contains 28,750 recorded hours across 114 languages, consisting of crowdsourced voice recordings with corresponding transcriptions.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- Common Voice 15
- Modality
- audio
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- common-voice-15|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Common Voice 15.
Which model scores highest on Common Voice 15?
Qwen2.5-Omni-7B is currently ranked first with 0.076 points.
What does Common Voice 15 measure?
Common Voice is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Version 15.0 contains 28,750 recorded hours across 114 languages, consisting of crowdsourced voice recordings with corresponding transcriptions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.