Capabilities
Explore what Whisper large-v3 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- fal
- Product
- Speech-to-Text
- Release Date
- Nov 6, 2023
- Data Policy
- Not specified
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try Whisper large-v3 by fal. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Whisper large-v3.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| fal | Not specified | Text | $0.0004 / minute | — | fal/whisper:fal |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | Not specified |
| Formats | mp3, mp4, mpeg, mpga, m4a, wav, webm |
Provider Notes
The five named slugs have model-specific schemas. fal/speech-to-text uses fal's direct SSE inference path; fal/speech-to-text-turbo and the other named models use fal's queue API. The normalized AudioLab response is returned only after the final provider result. fal also has an open-ended model marketplace, so fal/<owner>/<model> can be pinned dynamically; AudioLab sends only audio_url for unknown schemas and does not guess support for language, timestamps, diarization, or translation. Wizper and Whisper support translation; only fal/whisper supports diarization.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=fal/whisper' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | fal/whisper — Required model identifier. |
chunk_level | View Accepted Values |
max_segment_len / merge_chunks / version (Wizper) | View Accepted Values |
batch_size / num_speakers (Whisper) | View Accepted Values |
use_pnc (Canary speech-to-text) | View Accepted Values |
language / acceleration (Nemotron) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | Not specified |
| Formats | mp3, mp4, mpeg, mpga, m4a, wav, webm |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Nemotron ASR Multilingualfal | Not specified | $0.0068 / minute | — |
| Wizper (Whisper v3 Large)fal | Not specified | $0.0004 / minute | — |
| Canary Speech to Textfal | Not specified | $0.0408 / minute | — |
| Canary Speech to Text Turbofal | Not specified | $0.0408 / minute | — |
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
