Palatine Speech
Transcribe audio, diarize speakers, analyze sentiment, generate AI summaries, or use OpenAI-compatible LLM Chat Completions via Palatine. Keywords: n8n-community-node-package, n8n, palatine, speech-to-text, transcribe, transcription, stt, audio, ai, automation, voice-to-text, speech-recognition, audio-transcription, audio2text, audio-processing, diarization, speaker-diarization, speaker-segmentation, summarization, audio-summarization, sentiment-analysis, emotion-detection, tone-analysis, llm, chat-completions, openai-compatible, structured-output, json-schema
Actions6
- Audio Actions
- LLM Actions
Audio → Sentiment Analysis
AI-generatedSummary
Analyze sentiment or emotion in an uploaded audio file using Palatine Speech. Submit the binary file and, when the API returns a task ID, poll until the analysis completes.
Inputs
- binaryProperty (required) — Name of the input binary property containing the audio file; defaults to data.
- polling — Optional polling interval and attempt limit; defaults to 500 ms and 200 attempts. Values are clamped to 500–900000 ms and 1–1000 attempts; legacy values of 1000 ms and 300 attempts are reset to the defaults.
- requestOptions — Declared request settings for batching, SSL certificate validation, proxy, and timeout. The custom polling requests do not explicitly apply these settings.
Output shape
JSON items containing task: "sentiment", source_file, and sentiment, with the input binary data preserved.
sentiment contains the API response object or array, or a string for other response types. For asynchronous tasks, the completed payload is unwrapped from result, data, output, or response. Sentiment labels and scores are not specified by the node. source_file is empty if no filename is available. Task failure or exhaustion of the polling limit raises an error.