例: Sincere
Voice Affect: Calm, composed, and reassuring. Competent and in control, instilling trust.
Tone: Sincere, empathetic, with genuine concern for the customer and understanding of the situation.
Pacing: Slower during the apology to allow for clarity and processing. Faster when offering solutions to signal action and resolution.
Emotions: Calm reassurance, empathy, and gratitude.
Pronunciation: Clear, precise: Ensures clarity, especially with key details. Focus on key words like "refund" and "patience."
Pauses: Before and after the apology to give space for processing the apology.
例: Medieval Knight
Voice Affect: Deep, commanding, and slightly dramatic, reflecting the grandeur of ancient English storytelling.
Tone: Noble, heroic, and formal, capturing the essence of a medieval knight and epic adventure.
Emotions: A blend of excitement, anticipation, mystery, and the gravity of fate and duty.
Pronunciation: Clear, deliberate, with a slightly formal cadence; words like "hast", "thou", and "doth" are slowly emphasized to reflect archaic English pronunciation patterns.
Pauses: Pause after archaic English phrases like "Lo!" and "Hark!", and between clauses such as "Choose thy path" to emphasize the importance of the decision and allow the listener to reflect on the seriousness of the quest.
2件のコメント
Hacker Newsのコメント
これらのモデルの価格はElevenLabsよりかなり安い
"gpt-4o-mini-tts"モデルの場合、音声1分あたり$0.015で、ElevenLabsより85%安い"Business"プランは月額$1100で11,000分のTTSを提供し、1分あたり10セント課金OpenAIのJeffが新しいオーディオモデルをリリースしたことを告知
テキスト読み上げおよび音声認識モデルの信頼性の問題に言及
生成された音声と一緒に
"speech marks"を取得する方法を質問"speech marks"を説明最近の大規模なテキスト読み上げおよび音声認識モデルの進歩
"vibe"ボックスに入力したテキストに応じて、さまざまな抑揚や性格を表現できるNavy Seal copypastaを入力したときの反応
"vibe"指示に応じて異なる動作をする新しいモデルの声には微細な揺れがあり、Siriより劣ると感じる
OpenAIの公式ツールが新モデルの発表と結びついている
公式発表での重要な引用
"vibes"はUI上の指示事項である日本語も完璧に動きますね。