跳到正文
原文
Rohan Paul· @rohanpaul_ai · X·· 1 小时前AI 评分51
AI 导读

Podonos 发布 Onepin,定位为文本转语音之后的生产校验步骤,在旁白上线前逐行检查。它可用 400 万词发音词典核对人物和产品名、在语音播出前展开价格和日期、对每行音频的自然度、清晰度和词准确度打分,并用同一声音修复个别错词而无需重录;兼容 ElevenLabs、OpenAI、Google 等 30 多家语音服务,免费开始使用。作者补充其设计思路是校验比模型更重要,例如语音模型读 "03/04/27" 时会静默决定是三月还是四月,两种输出听感同样自信。

正文

A voice model reading "03/04/27" has to decide whether that's March or April. It decides silently, and the output sounds equally confident either way.

The interesting design choice in @OnepinAI: the check matters more than the model.

Built by Podonos, a voice AI evaluation company, it checks each line for naturalness and pronunciation and fixes the wrong words directly.
Script in, finished voiceover out.

引用Soohyun Bae@RealSoohyunBae
Your AI voice sounds human. So why can't it say your product's name? A great AI voice reads "Porsche Taycan" as TAY-can. Porsche says TIE-kahn. It guessed from the spelling, and nobody caught it, because nobody listens to line 1,200. Today we're launching Onepin: the production step after text-to-speech. It checks every line of voiceover before it ships using the voices you already work with. Onepin can: ➤ Check people's and product names against a 4-million-word pronunciation dictionary ➤ Spell out prices and dates before the voice speaks ➤ Score every line of audio for naturalness, clarity and word accuracy ➤ Fix the one wrong word in the same voice, without re-rendering the take Works with your voice subscription on @ElevenLabs, @OpenAI, @Google and 30+ more. No phonetic spellings to type. No re-rolls. No switching providers. Free to start, no credit card required. Hear the before and after in the thread ⬇️
在 X 查看被引用的帖子

来源:Rohan Paul · x.com