Files

Generate speech

Generate speech with a preset voice and save it in the workspace.

Speech generation uses a conformed Vercel AI Gateway model and is paid-only at launch.

Parameters#

textstringrequired

Text to speak, after outer whitespace is removed. Maximum 4,000 characters.

file_stemstringrequired

Output base name.

output_dirstringdefault: ""

Output directory. Defaults to /home/workspace/Audio.

voicestringdefault: eve

Preset voice: ara, eve, leo, rex, or sal.

formatstringdefault: mp3

Output format: mp3 or wav.

languagestringdefault: en

BCP-47 language code accepted by the selected model, such as en, es-MX, or auto.

speednumberdefault: 1

Speech speed from 0.7 to 1.5.

instructionsstringdefault: Natural, clear delivery.

Reserved delivery guidance. Current Grok TTS accepts only the default because its Gateway profile does not expose instructions.

modelstringdefault: ""

Optional public speech model ID.

voice_sample_pathstringdefault: ""

Reserved workspace voice sample path. Current profiles reject it.