Whisper Large v3 vs Whisper Large v3 Turbo
Two open-weight speech-to-text models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.
Inference APIs prices are read live from the price list.
- Cost: Both cost the same at list price.
Side by side
| Whisper Large v3 | Whisper Large v3 Turbo | |
|---|---|---|
| Served by | Inference APIs | Inference APIs |
| Model author | OpenAI | OpenAI |
| Model id | openai/whisper-large-v3 | openai/whisper-large-v3-turbo |
| Price | $0.001 / audio minute | $0.001 / audio minute |
| Capabilities | Speech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTT | Speech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTT |
| Weights | Open | Open |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | No per-minute or per-day request or token caps; usage draws on a prepaid balance |
| Speed | 0.047× real time (19.5 s clip in 0.92 s) | — |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | Whisper Large v3 | Whisper Large v3 Turbo | Difference |
|---|---|---|---|
| 1 hour of audio | $0.06 | $0.06 | — |
| 100 hours of audio | $6.00 | $6.00 | — |
| 1,000 hours of audio | $60.00 | $60.00 | — |
Both cost the same at list price.
When to choose which
- Broad language coverage with automatic language detection
- Files up to 100 MB and SRT or VTT subtitles straight from the API
- Speaker labels with diarize=true, at $0.002 a minute
- Hard audio or rare languages, where full Whisper Large v3 is more accurate
- Long files and batch jobs where speed matters more than the last bit of accuracy
- Code written for Groq's whisper-large-v3-turbo id
- An hour of audio in about 17 seconds for $0.06
Measured speed
Median of three runs on 2026-09-16: a 19.5-second mp3 clip, timed from upload to response. Expect ±30% with time of day. Method and raw numbers: speed measurements.
Trying both
Same endpoint, same key. Change one string:
for MODEL in "openai/whisper-large-v3" "openai/whisper-large-v3-turbo"; do
curl -s https://api.inferenceapis.com/v1/audio/transcriptions \
-H "Authorization: Bearer $INFERENCE_API_KEY" \
-F "model=$MODEL" -F "file=@meeting.mp3" | jq -r .text
doneFAQ
Which is cheaper, Whisper Large v3 or Whisper Large v3 Turbo?
Both cost the same at list price. The table above uses list prices: Whisper Large v3 $0.001 / audio minute; Whisper Large v3 Turbo $0.001 / audio minute.
How do I switch between them?
They are on the same endpoint and key. Change the model field from openai/whisper-large-v3 to openai/whisper-large-v3-turbo and nothing else.
Spotted a price or limit that has changed? Tell us and we will re-check the provider page.
