IBM Watson Speech to Text service
Use the IBM Watson Speech to Text service to transcribe spoken audio to written text. The documentation describes the Speech to Text service for IBM Cloud, IBM Cloud Pak for Data, and IBM Cloud Pak for Data as a Service.
- 4.5.x releases
- 4.6.x releases
- 4.7.x releases
- 4.8.x releases
- 5.0.x releases
- 5.1.x releases
- Making a basic HTTP speech recognition request
- Basic request example
- Making a multipart HTTP speech recognition request
- About Speech to Text
- Beta features
- Customization
- Audio support
- Speech recognition
- Language support
- Pricing
- Integrated use cases
- Product versions
- IBM and accessibility
- Accessibility
- Creating a custom acoustic model
- Troubleshooting the use of custom acoustic models
- Using a custom acoustic model for speech recognition
- Examples of using a custom acoustic model
- Add a word with the PUT method
- Add words with the POST method
- Adding an archive file
- Add audio to the custom acoustic model
- Adding an audio resource
- Adding an audio file