Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | fal-aiKokoro TTS (Hindi)Remove × | openaiwhisper-large-v3-turboRemove × | abr-aiabr-ai/niagara-9m-batch.enRemove × |
|---|---|---|---|
| What’s different | A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation. | Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper "Robust Speech Recognition via Large-Scale Weak Supervision" by Alec Radford et al.… | 0.009B parameters · 1 language · Encoder: State-space model · Decoder: CTC |
| Date | Feb 14, 2025Listed | Oct 2, 2024Listed | Oct 17, 2026Discovered |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.02/ 1K charactersfal · all routes ↗ | $3.33 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | See provider quotes |
| Provider endpoints | 1 endpoint → | 3 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 13.88% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 20.94% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | Not reported | 8.09% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 21.46% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 8.47% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 14.97% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | Not reported | 2.13% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 6.45% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | Not reported | 3.71% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 14.53% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | Not reported | 2.79% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 5.16% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | Not reported | 13.69% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 29.47% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | Not reported | 4.77% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 17.11% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | Not reported | 7.02% WER ↗openai/whisper-large-v3-turboLeaderboard entry | 7.33% WER ↗abr-ai/niagara-9m-batch.enLeaderboard entry |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | 0.009B |
| Audio input | Not reported | Supported | Supported |
| Transcription | Not reported | Supported | Supported |
| Open weights | Not reported | Supported | Not reported |