- NLU Node - Add Syntax to list of selectable features
- STT Node - Set correct content-type when File-Type reports a mime type of audio/opus for ogg;codec=opus files.
- Bump SDK Dependency to 3.18.2
- STT Node To use iam-utils in place of removed iam-token-manager
- STT Node removed codec setting as service can now automatically detect the codec of the input audio and supports more than codec=opus for ogg formats.
- TSS Node fix to add visibility check on tts.voices and not stt.models
- Assistant V1 Workspace Manager Node updated to reflect that in update mode, updated fields need a new_ prefix in their keys as part of the input json.
- NLC Node - migrate off deprecated methods
- NLC Node - Allow create of a classier to be based on a csv template node.
- Bump SDK Dependency to 3.15.0
- Added Portuguese (Brazilian) and Chinese (Simplified and Traditional) as output languages for Visual Recognition node.
- Added list voices and delete customisation methods to TTS Corpus Builder node.
- STT Node Changes
- Allowing SDK to manage IAM Tokens.
- Streaming mode for STT using IAM key now working.
- Fix to stream mode for max alternatives and smart formatting options
- Keywords, Word Confidence and Customization Weight can now be specified
- Allow Start and End data packets to be specified as JSON objects, as well as a stringified JSON objects.
- In line with SDK change use createLanguageModel() to create custom model
- Disable SSL Verification option for Assistant Node.
- Natural Language Understanding Node Changes
- Bump Natural Language Understanding to 2018-11-16
- Add Limit Categories and limit_text_characters options
- Allow JSON input into Personality Insights node.
- Japanese word count was causing a Node-RED crash when run in the cloud.
- Hungarian supported by Language Translator.
- New Document Language Translator node.
- New Assistant V2 Node.
- Discovery Node changes
- Bump Discovery to 2018-12-03
- Implement Query Notices method
- Bump dependency on file-type to 10.7.0
- Bump dependency on temp to 0.9.0
- Bump SDK Dependency to 3.11.0
- Bump Assistant version to 2018-09-20
- Bump Discovery version to 2018-08-01
- Bump Natural Language Understanding to 2018-09-21
- Bump Personality Insights to 2017-10-13
- Discovery New Environment Size is now a string
- Add Language Text to DropDrown for new supported languages in Translation Node.
- Natural Language Classifier updated for use of IAM key for authentication.
- Fix the Natural Language Understanding for bound IAM key service.
- German is a supported STT Language.
- Visual Recognition Key fix when migrating from unbound to bound service.
- Modify Discovery Query Builder Node to use
listCollectionFields
to determine query list.
- Allow version date for Assistant to be specified in
msg.params.version
to allow optional usage of beta version.
- Fix to how IAM Key for bound Visual Recognition is retrieved
- In this release STT in Stream mode with IAM Keys does not work.
- Assistant, Discovery, Language Identify, Language Translator, Natural Language Understanding, Personality Insights, Speech to Text, Text to Speech, Tone Analyzer nodes updated to allow for use of IAM key for authentication.
- Migrated STT node off deprecated methods.
- Fix to Tone Analyzer Node to preserve credentials on config reopen.
- Fix to Tone Analyzer to allow json objects and arrays as payload.
- Fix to STT where auto-connect was not being preserved when reopening configuration.
- Bump to 2018-03-05 version date for Discovery service.
- Move to V3 of Language Translator
- Migrated Discovery Nodes off deprecated methods.
- Remove Deprecated Retrieve and Rank Nodes
A collection of nodes to interact with the IBM Watson services in IBM Cloud.
- Assistant (formerly Conversation)
- Add conversational capabilities into applications.
- Discovery
- List environments created for the Discovery service
- Language Identification
- Detects the language used in text
- Language Translator
- Translates text from one language to another
- Natural Language Classifier
- Uses machine learning algorithms to return the top matching predefined classes for short text inputs.
- Natural Language Understanding
- Analyze text to extract meta-data from content such as concepts, entities, keywords ...
- Personality Insights
- Use linguistic analytics to infer cognitive and social characteristics from text
- Retrieve and Rank
- Creates a trainable search engine for your data
- Speech To Text
- Convert audio containing speech to text
- Text To Speech
- Convert text to audio speech
- Tone Analyzer
- Discover, understand, and revise the language tones in text.
- Visual Recognition
- Analyze visual appearance of images to understand their contents
Example usage flows can be found here node-red-labs
For simple typos and fixes please just raise an issue pointing out our mistakes. If you need to raise a pull request please read our contribution guidelines before doing so.
Copyright 2018 IBM Corp. under the Apache 2.0 license.