Whisper Diarization
whisper-diarizationWhisper Large v3 Turbo combined with pyannote 4.0 for speaker diarization, returning who-said-what segments with timestamps. Built by Thomas Mol. Returns a clean JSON of speaker-labeled segments, handy for meeting notes, interviews, and podcasts.
- Price
- ≈ US$0.0063/run
- Input → output
- Audio → Text
- Developer
- Community
- Updated
- September 23, 2026
Playground
Try Whisper Diarization
Input & output
This run
about US$0.0063 · 0.63 credits
US$0.0188 (1.88 credits) are reserved at the start; the actual GPU time is billed.
New here?
10 free credits (US$0.10) when you sign up with Google
Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 5 runs of this model.
Examples
Prompt
LLama, AI, Meta.
Output (JSON, shortened)
{ "language": "en", "segments": [ { "end": 4.48, "text": "Let me ask you about AI.", "start": 2.94, "words": [ { "end": 3.12, "word": "Let", "start": 2.94, "speaker": "SPEAKER_01", "probability": 0.685546875 }, { "end": 3.26, "word": "me", "start": 3.12, "speaker": "SPEAKER_01", "probability": 0.9990234375 }, { "end": 3.74, "word": "ask", "start": 3.26, "speaker": "SPEAKER_01", "probability": 0.998046875 }, { "end": 3.86, "word": "you", "start": 3.74, "speaker": "SPEAKER_01", "probability": 0.9921875 }, { "end": 4.1, "word": "about", "start": 3.86, "speaker": "SPEAKER_01", "probability": 0.9990234375 }, { "end": 4.48, "word": "AI.", "start": 4.1, "speaker": "SPEAKER_01", "probability": 0.966796875 } ], "speaker": "SPEAKER_01", "duration": 1.5400000000000005, "avg_logprob": -0.17070312313735486 }, { "end": 11.66, "text": "It seems like this year for the entirety of the human civilization is an interesting year for the development of artificial intelligence.", "start": 4.72, "words": [ {…Settings
- language
- en
About Whisper Diarization
Whisper Diarization is a model by Community in the Speech-to-text category. On Railwail, Whisper Diarization costs ≈ US$0.0063 per run.
Pricing
| Typical run (≈ 5 s on L40S) | US$0.0063 per run |
|---|---|
| GPU time (L40S) | US$0.00117 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = US$0.01
Cost calculator
Price calculator
Typical according to the provider: about 5.3 s
Total
US$0.63
63 credits
Per run
US$0.0063 · 0.63 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
whisper-diarization- Developer
- Community
- Category
- Speech-to-text
- Input
- Audio
- Output
- Text
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- September 23, 2026
Input parameters
Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.
file_urlrequiredURL of the audio file to transcribe and diarize
Type: TextDefault: –Allowed values: –promptOptional vocabulary or context hint
Type: TextDefault: –Allowed values: up to 1,000 characterslanguageOptional ISO-639-1 language code; auto-detected if omitted
Type: TextDefault: –Allowed values: –translateType: Yes/noDefault:falseAllowed values: –num_speakersOptional fixed speaker count; estimated if omitted
Type: IntegerDefault: –Allowed values: 1 to 50
Tags
- replicate
- whisper
- stt
- transcription
- diarization
- speaker-labels
- multilingual
Use cases
Frequently asked questions
What is Whisper Diarization?
Whisper Diarization is a model by Community in the Speech-to-text category.
How much does Whisper Diarization cost on Railwail?
On Railwail, Whisper Diarization costs ≈ US$0.0063 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
Which settings does Whisper Diarization support?
According to its input schema, Whisper Diarization knows these parameters: file_url, prompt (up to 1,000 characters), language, translate and num_speakers (1 to 50).
How fast is Whisper Diarization?
There are not enough measured runs of Whisper Diarization on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is Whisper Diarization better than Incredibly Fast Whisper?
That depends on the task. Whisper Diarization (Community) and Incredibly Fast Whisper (Community) are both models in the Speech-to-text category. The comparison page shows their prices and specifications side by side.
Compare Whisper Diarization and Incredibly Fast WhisperComparable models
All in this category- Incredibly Fast WhisperCommunity
Whisper Large v3 wrapped with Hugging Face Transformers optimizations (batched inference, flash attention) for very high throughput. Transcribes hours of audio in minutes on a single GPU. Maintained by Vaibhav Srivastav. Good when you need bulk transcription fast.
- WhisperOpenAI
OpenAI's Whisper running on Replicate. General-purpose speech recognition trained on 680k hours of multilingual audio. Transcribes and translates 99 languages, robust to accents and background noise, and outputs plain text, segments, or word-level timestamps.
- SeamlessM4TCommunity
Meta's SeamlessM4T multimodal translation model. Takes speech or text input and produces transcription or translation across about 100 languages, including speech-to-text and speech-to-speech. One model covers ASR plus cross-lingual translation without chaining separate systems.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.