Whisper
Whisper is a family of OpenAI automatic speech-recognition models that transcribe and translate spoken audio, including multilingual audio.
Data Analysis with LLMs
whisper-1 is the model identifier for the Whisper speech-transcription model in the OpenAI API.
- How it is used
- Transcribes recorded speech to text and supplies voice input to downstream applications.
- How deep it goes
- Defines Whisper as a multilingual Transformer model and demonstrates its API call, stopping short of explaining model internals.
- Examples
- Uses MP3 recordings, a literary quote, microphone input, and a voice interface that queries an SQLite database.
- What you can do after
- Operate Whisper via OpenAI’s Python library to transcribe supported audio files and feed transcripts into applications.
Build Applications with Local AI Models on a Mac
Whisper is an automatic speech-recognition model developed by OpenAI for transcribing multilingual audio.
- How it is used
- Adds speech-to-text input as a foundation for a voice-enabled chatbot.
- How deep it goes
- Explains the spectrogram, encoder, control tokens, and decoder, then summarizes audio requirements and model selection.
- Examples
- Uses a microphone-recording script and a transcription call returning text in a dictionary.
- What you can do after
- Apply it via MLX Whisper to transcribe audio and choose a model size for available memory.
Read how Build Applications with Local AI Models on a Mac explains Whisper →
Also covered in
Related concepts
- neural networkkind of · A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
- encoder-decoder transformerkind of · An encoder-decoder transformer is a neural-network architecture whose encoder processes an input sequence and whose decoder generates an output sequence conditioned on the encoded representation.
- speech recognitionimplements · Speech recognition is the computational task of converting spoken language in an audio signal into a machine-readable representation, typically text.
- audiouses · Audio is sound represented as a signal or data that can be stored, transmitted, processed, or reproduced.
- MLX Whisperimplemented by · MLX Whisper is a speech-recognition implementation that packages the Whisper model in a format optimized for Apple's MLX framework.
Questions about Whisper
What is Whisper?
Whisper is a family of OpenAI automatic speech-recognition models that transcribe and translate spoken audio, including multilingual audio.
Which Manning books explain Whisper?
Data Analysis with LLMs and Build Applications with Local AI Models on a Mac.
What should I know before learning Whisper?
Manning books that teach Whisper usually introduce microphone first.
What is Whisper a kind of?
Whisper is a kind of neural network. A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

