American English text to speech with thirteen US voices

Why a native American English voice matters

What people mean by an American accent in a voiceover is usually General American: the broadcast register, without the markers of Boston, the South or the Upper Midwest. Twelve of the thirteen voices here speak it; Spuds is the exception, a Southern grandpa voice for storytelling and character work. The r at the end of a syllable is pronounced, "t" between vowels softens the way it does in "water" and "better", and "can't" and "dance" take the flat vowel rather than the British one.

The accent matters most where the listener is deciding whether to keep listening: an explainer for a US audience, a phone system a customer calls, an ad. A British or neutral voice reading American copy is intelligible everywhere and still registers as foreign to the people it is aimed at, which is the one thing a voiceover cannot afford. Brittney and Jessica sit well on explainers and course material, Mark and Jon on corporate narration, Hope on younger and more conversational reads, Jamal on ads and trailers. Zara and Alex are made for creator and short-form content, Jessa for casual, off-the-cuff reads, Arabella for fiction and wellness narration, Peter and James for audiobooks and long narration, Spuds for tall tales and character reads.