Voices

List voices in a workspace

GET /api/v1/voices

🚀 New: Inworld TTS 1.5 Mini
This endpoint now uses Inworld TTS 1.5 Mini for ultra-low latency (~120ms), supporting 15 languages with instant voice cloning. No authentication required for listing voices.

Authorizations

Public Endpoint No Auth Required

This endpoint is publicly accessible. No API key or authentication required to list available voices.

For TTS synthesis, you'll need an API key. See Authentication docs.

Query Parameters

language string optional

Filter voices by language code. Default: en

Supported: en, es, fr, de, zh, ja, ko, and 8 more

Supported Languages (15 total)

English (en)

Spanish (es)

French (fr)

German (de)

Italian (it)

Portuguese (pt)

Chinese (zh)

Japanese (ja)

Korean (ko)

Russian (ru)

Polish (pl)

Dutch (nl)

Hindi (hi)

Hebrew (he)

Arabic (ar)

Response

200 Success

voices object[]

Array of voice objects

voiceId string

Unique identifier for the voice

displayName string

Human-readable name

langCode string

Language code (e.g., EN_US)

tags string[]

Descriptive tags for the voice

Available Voices

Alex male

professional

Brian male

conversational

Charlie male

warm

David male

authoritative

Ethan male

energetic

Hades male

deep

+ 6 more voices available

Tips for Voice Selection

Use contrasting voices (male/female) for better listener engagement
Match voice style to content — use "professional" for business topics
Higher quality models provide more natural speech but cost more