Search results
30 kwi 2020 · We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.
- Introducing the Realtime API
Today, we're introducing a public beta of the Realtime API,...
- Hello GPT-4o
As measured on traditional benchmarks, GPT-4o achieves GPT-4...
- Explore All Samples
Browse all samples
- Whisper Audio API FAQ
Whisper Audio API FAQ. General questions about the Whisper,...
- Introducing the Realtime API
1 paź 2024 · Today, we're introducing a public beta of the Realtime API, enabling all paid developers to build low-latency, multimodal experiences in their apps. Similar to ChatGPT’s Advanced Voice Mode, the Realtime API supports natural speech-to-speech conversations using the six preset voices already supported in the API.
13 maj 2024 · As measured on traditional benchmarks, GPT-4o achieves GPT-4 Turbo-level performance on text, reasoning, and coding intelligence, while setting new high watermarks on multilingual, audio, and vision capabilities. Text Evaluation. Audio ASR performance. Audio translation performance.
17 paź 2024 · New Release 3.9.0 simple-openai has been updated to support Audio on Chat Completions API. You can take a look at the following demo code to see async speech to speech interactions with a model (audio in, audio out):
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Browse all samples
Whisper Audio API FAQ. General questions about the Whisper, speech to text, Audio API. Updated over 9 months ago. OpenAI's Whisper models have the potential to be used in a wide range of applications, from transcription services to voice assistants and more.
