Parakeet TDT 0.6B v3 vs Whisper Large v3
Two speech-to-text models compared on price, context, capabilities and measured speed. External prices are public list rates verified 2026-09-16; Inference APIs prices are live.
| Parakeet TDT 0.6B v3 | Whisper Large v3 | |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Model id | nvidia/parakeet-tdt-0.6b-v3 | openai/whisper-large-v3 |
| Price | $0.002 / audio minute | $0.002 / audio minute |
| Capabilities | Speech to text, Very fast, Timestamps, 25 languages | Speech to text, 99 languages, Timestamps, SRT / VTT |
| Weights | Open | Open |
| Availability | Available on Inference APIs | Available on Inference APIs |
| Rate limits | No daily caps; pay per request | No daily caps; pay per request |
| Real-time factor | 0.036× (19.5s clip in 0.7s) | 0.047× (19.5s clip in 0.92s) |
Cost for 10 hours of audio
Both cost the same for this workload at list price.
Measured speed
Speed figures for Inference APIs models are medians of three runs from a European client on 2026-09-16, against the public endpoint, using a ~120-word generation prompt (chat), a 300-character paragraph (speech) or a 19.5-second clip (transcription). External models are not measured here; treat "not measured" as unknown, not slow.
When to pick which
- Parakeet TDT 0.6B v3 — NVIDIA's very fast English-first transcription model with accurate timestamps; ideal for long recordings and batch jobs.
- Whisper Large v3 — OpenAI's multilingual speech recognition model on the standard /v1/audio/transcriptions endpoint — same request shape as OpenAI and Groq.
Try Parakeet TDT 0.6B v3
Same OpenAI request shape; the change is the base URL and key. Full parameters, aliases and pricing on the model page.
External prices and limits come from the linked provider pages and were verified on 2026-09-16. Spotted a change? Tell us.