Voices & languages.
Ten distinct personalities, twenty-three languages, all available on every plan at no extra cost. Voices can be switched per request and even within a single WebSocket session.
The voice library
Each voice ships with a tag describing its default register. You can soften, brighten, or slow any voice with the per-request speed and inline expression tags.
| id | Name | Register | Best for |
|---|---|---|---|
| meera | Meera | Warm, expressive | Customer support, friendly agents, conversational |
| arjun | Arjun | Authoritative baritone | Announcements, formal IVR, news |
| kabir | Kabir | Bright, energetic | Ads, sports, promotional reads |
| vikram | Vikram | Calm, wise | Guided meditation, mentoring, support |
| anaya | Anaya | Gentle, lyrical | Soft reassurance, audiobooks, lullabies |
| saanvi | Saanvi | Poised, cinematic | Storytelling, trailers, long-form narration |
| noor | Noor | Crisp, urbane | Editorial reads, podcast hosting |
| aria | Aria | Sparkling, youthful | Lifestyle apps, social, e-commerce |
| orion | Orion | Deep, measured | Documentaries, premium voiceover |
| luma | Luma | Cool, conversational | Sales agents, outbound calling |
Hear them all on the samples page or in the home-page studio.
Languages
One model, twenty-three languages. The phonemiser, acoustic model, and vocoder were trained jointly across all of them, so accent-mixing in a single sentence works without an extra round-trip.
| Code | Language | Quality tier |
|---|---|---|
| en | English | First-class |
| hi | Hindi | First-class |
| es | Spanish | First-class |
| fr | French | First-class |
| de | German | First-class |
| it | Italian | First-class |
| pt | Portuguese | First-class |
| nl | Dutch | Standard |
| pl | Polish | Standard |
| ru | Russian | Standard |
| tr | Turkish | Standard |
| ar | Arabic | Standard |
| ko | Korean | Standard |
| ja | Japanese | Standard |
| vi | Vietnamese | Standard |
| id | Indonesian | Standard |
| el, bg, da, fi, hr, lt, sl, sv | European long-tail | Beta |
Custom voices
Voice cloning from a 30-second sample is available on the Enterprise plan. Clones are private to your workspace, encrypted at rest, and can be deleted (along with all derived audio) on demand for GDPR compliance.
Contact us to enable cloning on your account.