Gnani.aiText-to-speech

timbre-v3.0

JSON

Timbre v3.0 TTS GA streaming, http, websocket

Indic text-to-speech with 34 voices that each speak all ten supported languages, plus inline audio tags for non-verbal cues.

01 Price

Gnani.ai doesn't publish a per-unit price for this model.

02 Languages 10

03 Features 1 of 8 listed

  • Emotion control
  • Voice cloningnot listed
  • Voice designnot listed
  • SSMLnot listed
  • Phoneme inputnot listed
  • Speed / prosody controlnot listed
  • Style controlnot listed
  • Multi-speakernot listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Voices 34 compatible, browse all

  • No sample published

    Anitasingh

    Firm yet empathetic

    female / Bengali (IN) +9
    Collections, payment reminders, BFSI

    Anitasingh
  • No sample published

    Arko

    Deep authoritative baritone

    male / Bengali (IN) +9
    Narration, announcements, brand

    Arko
  • No sample published

    Avinash

    Calm and captivating

    male / Bengali (IN) +9
    Brand films, e learning, advertising

    Avinash
  • No sample published

    Chetana

    Soft and intimate

    female / Bengali (IN) +9
    Audiobooks, romance, ASMR style content

    Chetana
  • No sample published

    Devansh

    Soft and sincere

    male / Bengali (IN) +9
    Storytelling, drama, emotional content

    Devansh
  • No sample published

    Harshad

    Deep and grounded

    male / Bengali (IN) +9
    Conversational IVR, regional engagement

    Harshad

05 Get this record

curl https://voicedex.dev/v1/providers/gnani/models/timbre-v3.0

Free, no key needed. Use model id timbre-v3.0 with Gnani.ai's own API. API reference.

Esc

↑↓ move↵ open