Skip to Main Content
Introduction to OCI Speech

About This Workshop

Youtube Video

About This Workshop
The OCI Speech Service harnesses the power of spoken language by allowing developers to easily convert file-based audio data containing human speech into highly accurate text transcriptions. This service is useful for customers who would wish to use speech recognition in their applications and be able to build end user facing speech experiences to allow generation of transcriptions from given audio files( Audio files which are present in OCI Object Store only). The speech service is an OCI Native Application which can be accessed via web applications, REST API, CLI and SDK. We can integrate other features like enabling E-mail. notifications, triggering functions after transcription of given audio files is completed.

Workshop Info

  • Create a bucket and upload files
  • Transcribe audio with the OCI console
  • Access OCI speech with SDKs
  • Access OCI speech with CLI
  • Access OCI speech with REST APIs
  • Use OCI speech with datascience notebook session
  • Enable E-mail notifications for OCI speech transcription job status
  • Trigger functions on completion speech transcription jobs
  • Familiar with OCI Policy and SDK/CLI setup.
  • Familiar with Python/Java programming for SDK usage is strongly recommended.
  • Familiar with OCI  services DataScience is recommended, but not required.

Other Workshops you might like