Provides instant answers to user questions using Perplexity AI. Accepts a text prompt and session ID as input, sends the prompt to Perplexity's LLM (sonar-pro model), and returns a concise, text-based response. The workflow triggers via an API endpoint and outputs the answer directly.
Select the reason for reporting
Describe the issue in detail
The Focus Group simulator synthesizes AI-generated insights for focus group discussions to support preliminary research. It takes participant input and queries various AI models, including Perplexity, OpenAI, Diffbot, DeepSeek, xAI Grok, Anthropic Claude, Groq, and Gemini, in parallel to gather a range of perspectives from their knowledge bases. The workflow processes these inputs into a simulated report.
Generates insights by engaging in AI-driven conversations on a given topic using current date and time as context. Utilizes Perplexity AI and OpenAI to simulate interactive chats based on the topic and contextual time data, then consolidates the responses into a unified output.
Researches competitors for a provided company and context, returning a JSON of companies and relevant fields. Accepts a user-provided query as input, processes the query using Perplexity AI to obtain an accurate and relevant response, and then outputs this response as the answer.
Creates a 1 minute podcast about the received text. Accepts a text input and uses OpenAI to generate a script, then employs ElevenLabs to convert the interpreted text into speech, saving it as an audio file. Returns the audio file as a url.
Converts HTML content into a downloadable PDF file. Accepts raw HTML as input, generates a unique filename, uses a Puppeteer-based service to render the HTML as a PDF, stores it in Google Cloud Storage, and provides a public download URL as output.
Converts spoken audio into translated speech in another language. Accepts an audio file and a target language, transcribes the audio using OpenAI Whisper, translates the text with GPT, synthesizes the translated speech using OpenAI TTS, uploads the audio, and returns the transcription, translation, and a link to the new audio file.
