Changelog

Copy

• Copy for LLM

  Copy page as Markdown for LLMs
• View as Markdown

  Open this page as Markdown
• Open in ChatGPT

  Get insights from ChatGPT
• Open in Claude

  Get insights from Claude
• Connect to Cursor

  Install MCP server on Cursor
• Connect to VS Code

  Install MCP server on VS Code

2022-08-02

Version 2.17.1

Added

• skip_punctuation parameter to the Streaming Speech-to-Text API Client
• skip_punctuation parameter to the Asynchronous Speech-to-Text API Client

2022-05-19

Version 2.17.0

Added

• language parameter to the Streaming Speech-to-Text API Client

2022-05-13

Version 2.16.0

Added

• notification_config and source_config parameters to all job submissions

Added

• Support for Language Identification API

• Support for Sentiment Analysis API

Deprecated

• media_url option. Use source_config instead

• callback_url option. Use notification_config instead

2022-04-25

Version 2.15.0

Added

• Support for Topic Extraction API

• speaker_names option to asynchronous client for human transcription

2022-01-31

Version 2.14.0

Added

• transcriber to asynchronous client
• verbatim, rush, test_mode and segments_to_transcribe options to asynchronous client for human transcription
• start_ts and transcriber to streaming client

2021-10-12

Version 2.13.0

Added

• detailed_partials parameter to the streaming client
• CI now runs on GitHub Actions. This replaces Travis CI.

2021-03-09

Version 2.12.0

Added

• custom_vocabulary_id option to enable job submission with the id of a pre-submitted custom vocabulary

2021-01-17

Version 2.11.0

Added

• language job option to the Asynchronous Speech-to-Text API. Transcribe audio in languages other than English. See Asynchronous Speech-to-Text API docs for the full list of supported languages.
• Relax dependency pinned version requirements.

2020-07-22

Version 2.9.0

Added

• delete_custom_vocabulary(id): Delete your custom vocabulary by id
• get_list_of_custom_vocabularies(): Get a list of recent custom vocabulary submissions' information
• remove_disfluencies job option for the streaming client: Remove filler words (disfluencies) from the resulting transcript. This option was previously available for the Asynchronous Speech-to-Text API client.

Changed

• Improved examples

Fixed

• Bug fixes and improvements