Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | sesamecsm-1bRemove × | Briaremove_background_guidedRemove × | abr-aiabr-ai/niagara-84m-batch.enRemove × |
|---|---|---|---|
| What’s different | CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio… | Prompt-guided background removal by Bria: tell it what to keep or what to remove and get a clean cutout with true transparency, at the original resolution with the original pixels untouched. Trained… | 0.084B parameters · 1 language · Encoder: State-space model · Decoder: CTC |
| Date | Mar 15, 2025Listed | Oct 14, 2026Listed | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.007/ 1K charactersDeepInfra · all routes ↗1,000 input characters | See provider quotes | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 12.01% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | Not reported | 10.83% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 10.41% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | Not reported | 3.09% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | Not reported | 7.6% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | Not reported | 2.61% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | Not reported | 20.16% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | Not reported | 8.82% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | Not reported | 4.33% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | 1B | — | 0.084B |
| Audio input | Not reported | Not reported | Supported |
| Transcription | Not reported | Not reported | Supported |