Creates a variation of a given image. By default a 1024×1024 image is created. 256×256 or 512×512 are also creatable. The given image must be a square image less than 4MB. The maximum number that can be created at once is 10.
Creates an image given a prompt. By default a 1024×1024 image is generated, but you can change it to 256×256 or 512×512. Note that PROMPT must be defined within 1000 characters.
This is a process to centrally manage responses to inquiries via web forms and phone calls.
After receiving an inquiry, a draft of the inquiry response is automatically requested to the AI chat (ChatGPT).
The person in charge uses the draft to create a response text.
Communicates with OpenAI API (ChatGPT); the default MODEL is “gpt-4” (configurable). Supports almost all Chat features, such as re-asking based on histories and/or parameters; sampling temperature-Top_P, Presence-Frequency penalty, Logit bias.
Starts a conversation with the OpenAI API (ChatGPT). The MODEL used is “gpt-4” by default (configurable). A response (COMPLETION) to an instruction question (PROMPT) is automatically obtained.
Accepts questions and designates personnel to create the answer. After receiving a question via a web form or email, the person responsible for preparing the answer will be appointed at the Step [2. Jurisdiction to answer]. Answers are drafted by AI, and person responsible completes it. At the [5. Reviewing terminology and legal] Step the content of the answer is checked, and if approved it will proceed to the following Step.
Transcribes audio and video files in caption format WebVTT, using the OpenAI API “whisper-1” model by default (configurable) to convert audio data into text data. Set abbreviations and technical terms as PROMPT for more accurate transcription.
Translates audio into English. English text data is generated from sound or video file containing Japanese or other, using the OpenAI API “whisper-1” model. Abbreviations and technical terms can be set as PRMOPT to achieve more accurate translation.
Transcribes from audio file. The “whisper-1” model in the OpenAI API converts speech data into text data. If set abbreviations and technical terms as summary (PRMOPT), more accurate data conversion will be achieved.
Communicates with OpenAI API (ChatGPT). Instructions with conversation history and/or advanced parameters (PROMPT) are possible; Sampling temperature, Sampling Top_P, Presence penalty, Frequency penalty, Logit bias. Model ID used is “gpt-3.5-turbo”.
Starts a conversation with the OpenAI API (ChatGPT). The model ID used is “gpt-3.5-turbo”. A response (COMPLETION) to an instruction question (PROMPT) is automatically obtained.