Wiro - PersonaPlex - Speech-to-Speech Conversion
AI-generatedOverview
This node performs speech-to-speech conversion using the PersonaPlex AI service by Wiro. It takes a text prompt and voice parameters to generate speech output with customizable voices. This is useful for creating voiceovers, conversational agents, or any application requiring natural or expressive speech synthesis.
Use Case Examples
- Generating a voiceover from a text script using a natural female voice.
- Creating an expressive male voice response for a chatbot.
Properties
| Name | Meaning |
|---|---|
| Prompt | The text prompt to be converted into speech. |
| Voice | The voice style to use for speech synthesis, including natural conversational or more expressive variety voices. |
| Text Temperature | Controls the randomness of generated text responses, affecting creativity and variability. |
| Audio Top K | Limits audio generation to the top K most likely tokens, controlling audio output diversity. |
| Text Top K | Limits text generation to the top K most likely tokens, controlling text output diversity. |
| Seed | Seed value to influence reproducibility of generated speech output. |
Output
JSON
taskid- Identifier of the speech synthesis task.url- URL to access the generated speech audio once the task is completed.status- Status of the speech synthesis task, e.g., 'completed' or 'failed'.
Dependencies
- Wiro API key and secret credentials for authentication
Troubleshooting
- If the node throws an error about missing or invalid task ID or socket access token, verify that the Wiro API credentials are correct and the API service is reachable.
- Task status values '-1', '-2', '-3', or '-4' indicate failure states; check the prompt and parameters for validity and retry.
- Network issues or incorrect authentication headers can cause HTTP request failures; ensure proper API key and secret are provided.