Sobmit Docs

Audio Generation node

Audio Generation node card

The Audio Generation node synthesizes speech audio from text (text-to-speech) using a speech model (via Replicate).

Handles

HandlePurpose
promptThe text to speak (required)

Configuration

  • Model — the speech model (e.g. jaaari/kokoro-82m).
  • Voice — the voice to use (model-dependent, e.g. Kokoro’s af_bella).
  • Speed — playback speed (where supported, e.g. Kokoro 0.5–2×).

Not every model honors every field. Kokoro encodes the language in the voice id (e.g. af_* = American English, zf_* = Chinese), so there is no separate language selector — the upstream Prompt or Agent node has to produce the right text. Bark is text-only (no voice/speed levers).

Example

Prompt node → Audio Generation:

prompt: "Welcome to Sobmit — the visual workflow builder for AI agents."
model: jaaari/kokoro-82m
voice: af_bella

The generated audio ({ dataUrl, mime }) becomes the payload, rendered as an inline player on the card.

Notes

  • The text is required — the engine fails fast without it.
  • The card shows an inline <audio> player and artifact history.

Related