All tasks / Models
Solaria-3
Gladia's speech-to-text model for batch and real-time transcription with audio enrichment.
- Gladia
- Closed
- Released 10 Jun 2026
Where it ranks
- ATranscriptionModels · Cloud · 3.2% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)
Facts
- Vendor
- Gladia
- Family
- Gladia Solaria
- Released
- 10 Jun 2026
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.01 per minute of audio (Artificial Analysis lists $10.16 per 1,000 minutes (Solaria-3); divided by 1,000. Official self-serve async rate is EUR 0.16/hour.)
- Access
- Free tier available
- Last verified
- 19 Oct 2026
Price from gladia.io, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech to Text: AA-WER v2 (non-streaming) | 3.2% | Solaria-3, GladiaAA-WER v2 (non-streaming), provider Gladia; embedded value 0.0323 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
| Hugging Face Open ASR Leaderboard (English, short-form average WER) | 6% | gladia/solaria-3Average WER over the board's default datasets (English short-form, version 17-10-2026); rank 22 of 56; read from the Space's /config table data. | 17 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet.
Earlier versions
- Solaria-1 · 2 Apr 2025