IBM WatsonText-to-speech

ibm-neural

JSON

IBM Enhanced neural voices TTS GA Provider default streaming, http, websocket

Enhanced neural (V3) voices; the service default voice is en-US_MichaelV3Voice.

01 Price

IBM Watson doesn't publish a per-unit price for this model.

02 Languages 9, 13 with regional variants

03 Features 2 of 8 listed

  • Emotion controlnot listed
  • Voice cloningnot listed
  • Voice designnot listed
  • SSML
  • Phoneme input
  • 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 25 compatible, browse all

  • No sample published

    Birgit

    Birgit: Standard German (Standarddeutsch) female voice. Dnn technology.

    female / German (DE)

    de-DE_BirgitV3Voice
  • No sample published

    Dieter

    Dieter: Standard German (Standarddeutsch) male voice. Dnn technology.

    male / German (DE)

    de-DE_DieterV3Voice
  • No sample published

    Erika

    Erika: Standard German (Standarddeutsch) female voice. Dnn technology.

    female / German (DE)

    de-DE_ErikaV3Voice
  • No sample published

    Charlotte

    Charlotte: British English female voice. Dnn technology.

    female / English (GB)

    en-GB_CharlotteV3Voice
  • No sample published

    James

    James: British English male voice. Dnn technology.

    male / English (GB)

    en-GB_JamesV3Voice
  • No sample published

    Kate

    Kate: British English female voice. Dnn technology.

    female / English (GB)

    en-GB_KateV3Voice

05 Get this record

curl https://voicedex.dev/v1/providers/ibm/models/ibm-neural

Free, no key needed. Use model id ibm-neural with IBM Watson's own API. API reference.

Esc

↑↓ move↵ open