FrankLab VOLNA icon

FrankLab VOLNA

Generate and process speech, voice, dubbing, and audio with FrankLab VOLNA.

Actions16

Speech → Text to Dialogue

AI-generated

Summary

Generate a dual-voice dialogue audio from provided text by specifying two voice IDs. Optionally include additional JSON fields and choose whether to wait for task completion.

Inputs

  • Text (required) — The text content that will be transformed into a dialogue audio.
  • Voice ID (required) — The voice ID for the first speaker in the dialogue.
  • Second Voice ID (required) — The voice ID for the second speaker in the dialogue.
  • Additional JSON — Extra JSON fields to customize the FrankLab API request; media URLs must be publicly accessible via http or https.
  • Wait for Completion — Whether to wait for the dialogue generation task to complete before returning the results.

Output shape

a JSON object representing the task result, including status, task ID, audio (dialogue) URL, and possible cost and error information.

If 'Wait for Completion' is true, the operation polls until the task is finished, returning final results; otherwise it returns the initial task details. The output includes fields like 'status', 'taskId', 'audioUrl', 'resultUrl', 'downloadUrl', and 'error' if any. Additional cost fields may be included when available.

Examples

Example 1: To generate a dialogue audio from a script where two speakers alternate, specify the script text under 'Text', provide the two desired voice IDs, optionally add additional parameters in JSON format, and optionally set waiting behavior. The output will contain URLs to access or download the generated dialogue audio.

Fill 'Text' with dialogue content, 'Voice ID' with the first speaker's voice identifier, 'Second Voice ID' with the second speaker's voice identifier, set 'Additional JSON' for any extra API customization if needed, and set 'Wait for Completion' to true if you want the node to return when generation finishes.

Links

Discussion