Get a weekly rundown of the latest AI models and research... subscribe!

Whisper Wordtimestamps



Whisper is an AI model developed by OpenAI that can convert textual input into natural-sounding speech. It has been enhanced to include the functionality of word_timestamps, allowing users to access timestamps indicating when each word is spoken in the generated audio. These timestamps can be helpful for various applications such as aligning the generated audio with a corresponding text or performing analysis and processing on specific parts of the audio.

Use cases

The addition of word_timestamps to OpenAI's Whisper model opens up a range of possibilities for developers and researchers. One potential use case is in the field of transcription, where the timestamps can greatly simplify the process of aligning generated audio with its corresponding text. This can save time and effort for transcriptionists and improve the accuracy of the final text. Moreover, the word_timestamps can be leveraged in audio analysis applications to enable precise processing on specific parts of the audio, such as identifying and extracting specific words or phrases. This can be especially beneficial in scenarios where audio data needs to be analyzed and searched efficiently. Additionally, the availability of word_timestamps can create opportunities for innovative products such as audio-based search engines, interactive audio-driven applications, or tools that assist users in studying or learning new languages. In summary, the inclusion of word_timestamps in Whisper enhances the model's versatility and opens up various practical uses and potential products in the field of text-to-audio conversion.



Cost per run
Avg run time
Nvidia T4 GPU

Creator Models

No other models by this creator

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Whisper Wordtimestamps model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameWhisper Wordtimestamps
openai/whisper with exposed settings for word_timestamps
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction HardwareNvidia T4 GPU
Average Completion Time-