FrankLab VOLNA icon

FrankLab VOLNA

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

Actions16

Speech → Speech to Text

AI-generated

Summary

Convert speech from an audio file accessible via a public URL into text by submitting the audio URL and optional parameters to FrankLab's VOLNA speech-to-text API endpoint, with an option to wait for the transcription task to complete before returning.

Inputs

  • Audio URL (required) — A public HTTP or HTTPS URL of the audio file to transcribe to text.
  • Additional JSON — Additional JSON fields for the FrankLab API request. Media URL fields must use public HTTP or HTTPS URLs. Used to specify advanced transcription options.
  • Wait for Completion — Boolean flag to indicate whether the node should wait until the transcription task finishes and return the completed result, or return immediately after task submission.

Output shape

A single record containing transcription results and metadata about the transcription task.

If 'Wait for Completion' is true, the output includes the final transcription text and related data. The output contains properties such as task ID, status, transcription text, possible error messages and any associated cost fields returned from the FrankLab VOLNA API.

Examples

Example 1: Basic speech to text

Set 'Audio URL' to a valid public audio file URL, leave 'Additional JSON' empty, and optionally enable 'Wait for Completion' to receive the completed transcription in one step.

Links

Discussion