[email protected]

[FelixWaweru]

Releases

• [email protected]

Description

• ElevenLabs_Node V2 available!

✨ New Features

• Set up the API Key and Voice ID when importing the package
• Added Speaker Boost to TTS
• Added Style Exaggeration to TTS.
• Improved textToSpeechStream to handle multiple response types i.e ArrayBuffer, Json or Stream
• Improved Documentation to include code snippets and variable types

⛰ Major Changes

• API Key and Voice ID are setup when importing the package
• textToSpeech and textToSpeechStream functions no longer require you to pass the API Key on declaration
• You can optionally pass the Voice ID to the textToSpeech and textToSpeechStream functions if you wish to use different IDs from the default
• All Functions that require variables use an object i.e

// V2
textToSpeech({
    fileName: "audio.mp3",
    textInput: "mozzy is cool",
    voiceId: "21m00Tcm4TlvDq8ikWAM",
    stability: 0.5,
    similarityBoost: 0.5,
    modelId: "elevenlabs_multilingual_v2",
    style: 1,
    speakerBoost: true
  });

// Or

textToSpeech({
    "audio.mp3",
    "mozzy is cool",
    "21m00Tcm4TlvDq8ikWAM",
    0.5,
    0.5,
    "elevenlabs_multilingual_v2",
    1,
    true
  });

// V1
textToSpeech(
    "audio.mp3",
    "mozzy is cool",
    "21m00Tcm4TlvDq8ikWAM",
    0.5,
    0.5,
    "elevenlabs_multilingual_v2",
    1,
    true
  );

---

This discussion was created from the release [email protected].