Text to Speech

POST/api/v2/text-to-speech

25 credits per generation

Generate spoken audio from text in any voice your team owns — built-in voices, premium presets, or custom cloned/designed voices.

Request body

Voice Id *voice_id

Generate an API key to pick from your voices.

Voice to speak in. Accepts a voice id from GET /api/v2/voices, a voice created via /api/v2/voice-clone or /api/v2/voice-design, or a built-in/premium preset voice id. Cloned custom voices work exactly like any other voice.

Text *text

The text to convert to speech.

Language language

Spoken language (ISO 639-1 code). Default: en.

Speed speed

Speech speed (0.6–1.5). Default: 1.0.

Volume volume

Output volume (0.5–2.0). Default: 1.0.

Emotion emotion

Emotional tone of the delivery. Default: neutral.

Output Format output_format

Audio container format. Default: mp3.

Workspace Id workspace_id

Request example

curl -X POST "https://influencerstudio.com/api/v2/text-to-speech" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Output

Run the model to see results

Real outputs will stream into this panel as the request completes.