Callr Actions: DragonHD and MAI natural voices, and text-to-speech on your own Azure or ElevenLabs account

Callr Actions gets two new families of natural voices, and can now synthesize your prompts on your own Azure or ElevenLabs account.

• DragonHD voices. Azure DragonHD voices are available in en-US, en-GB, de-DE, es-ES, fr-FR and it-IT. Their names end in :DragonHDLatest or :DragonHDOmniLatest, for example en-US-Ava:DragonHDLatest or fr-FR-Remy:DragonHDLatest.
• MAI voices. Microsoft MAI voices are available in en-US, de-DE, es-ES, fr-FR, it-IT and nl-NL. Their names end in :MAI-Voice-2.1, for example en-US-Harper:MAI-Voice-2.1 or fr-FR-Marc:MAI-Voice-2.1.
• Same price. DragonHD and MAI voices cost the same as standard voices.
• Everywhere you speak. Set them in tts.voice of play@v3, say@v3, gather@v4, recognize@v3 and amd@v3, or once for the scenario in defaults.voice.
• Your own Azure or ElevenLabs account. defaults.textToSpeech.engine now accepts azure or elevenlabs, with your key in config. Synthesis runs, and is billed, on your account. The engine applies to the whole scenario.

defaults:
  voice: en-US-Ava:DragonHDLatest

branches:
  inbound-call:
    actions:
      - action: play@v3
        params:
          tts:
            text: Thanks for calling. How can we help?
            voice: en-US-Harper:MAI-Voice-2.1

defaults:
  voice: JBFqnCBsd6RMkjVDRZzb
  textToSpeech:
    engine: elevenlabs
    config:
      key: your-elevenlabs-api-key
      modelID: eleven_flash_v2_5

See the Voices & Audio guide for the full voice list and the Azure setup.