I present a YouTube channel in English. The channel runs AI models against each other on the same challenge and compares the answers. I want two lines of Mandarin in this video, said out loud, in my own voice, and I do not speak Chinese. I cannot read characters. I have never heard most of these sounds.
What I can do is read English. That is the entire tool you have to work with: you write something in English letters, I say it into a microphone, and a Chinese listener either understands me or does not.
Two quips. One sentence each, at most fourteen characters each, shorter is better — I have to say them on camera from memory.
Quip 1 — about Claude Fable 5 refusing most of the Johanna Benchmark challenges on cybersecurity concerns.
Quip 2 — Pick a Chinese proverb, idiom or set expression and use it to say something about the "China vs. the U.S." AI race. Use a relatively unknown one... not one of the top 30 examples that a Chinese person would think of first. Be creative, artistic, deep in your choice, even though it's then used to crack a joke.
Both quips are jokes and they are supposed to bite. Sharp, witty, outrageously funny, not diplomatic. A quip that is careful and balanced has failed this. So has one that hedges, and so has one that explains itself inside the joke. Do not soften it to be fair to everyone involved.
Respell it for an English mouth, not in pinyin. Pinyin is a spelling system for people who already know how it sounds. I do not, so I will read it as English and produce the wrong sound with total confidence: qi comes out "kwee" when it is "chee", xie comes out "zy" when it is "shyeh", zhong comes out "zong" when it is "jong", cai comes out "kay" when it is "tsigh", ren comes out "wren" when it is "run", shi comes out "shy" when it is "shrr". Write the syllables the way an English speaker has to see them in order to say them. If your respelling would survive being read aloud by someone who does not know a single Chinese word, it is right.
Mark the tone on every syllable, with these arrows and no others. I have never spoken a tonal language and I need to see the shape of my voice:
| Tone | Arrow |
|---|---|
| 1st, high and flat | → |
| 2nd, rising | ↗ |
| 3rd, dipping | ↘↗ |
| 4th, falling sharply | ↘ |
| neutral, no tone at all | · |
Respell what is actually said, not what the dictionary lists. Tones change when syllables sit next to each other. Write the spoken version, and say in tone_changes which syllables you changed and why.
One row per character. The characters, the respelling and your notes are going on screen together, lined up, so a viewer can see which sound belongs to which character. syllables must have exactly one entry per Chinese character in chinese, in order, with no rows for punctuation and no two characters merged into one row.
Warn me about the sounds English does not have. Tell me what to do with my mouth. "Say 'she' but with the tip of your tongue pressed down behind your bottom teeth" is useful. "Alveolo-palatal fricative" is not.
Pick the sayable version. If the funnier line needs a sound I would need three weeks to learn, write the slightly less funny line I can actually land. Say so if you made that trade.
You should know what is about to happen to your answer, because it changes what a good answer is.
I am going to paste your chinese into Google Translate to check it means what you told me it means. Then I am going to read your read_aloud into Google Translate's Chinese voice input and see what it thinks I said. What comes back gets compared, on camera, to the characters you started from.
So this is not scored on whether your transcription is correct by any standard. It is scored on whether a machine can understand your sentence from an English speaker's mouth reading English letters — and on whether the joke is funny in Chinese, which is a separate question from whether it is funny translated.
Raw JSON, nothing else — no markdown fence, no preamble, no commentary afterwards. Exactly this shape:
{
"quips": [
{
"id": "fable",
"chinese": "...",
"english": "...",
"joke": "...",
"syllables": [
{ "hanzi": "...", "say": "...", "tone": 0, "arrow": "..." }
],
"read_aloud": "...",
"tone_changes": "",
"watch_out": ""
},
{
"id": "proverb",
"chinese": "...",
"english": "...",
"joke": "...",
"syllables": [
{ "hanzi": "...", "say": "...", "tone": 0, "arrow": "..." }
],
"read_aloud": "...",
"tone_changes": "",
"watch_out": ""
}
],
"proverb": {
"text": "...",
"literal": "...",
"means": "...",
"why_this_one": "..."
},
"tones": [
{ "tone": 0, "arrow": "...", "what_to_do": "..." }
],
"hard_sounds": [
{ "sound": "...", "what_to_do": "..." }
],
"notes": "..."
}
chinese — the quip in simplified characters.english — a literal gloss, so I can check it against Google Translate.joke — one line: what makes it funny. I cannot read the Chinese and I have to explain the joke on camera.syllables — one entry per character. say is the respelling of that one syllable, tone is the number 1–4 as it is actually said (0 for a neutral syllable), arrow is that tone's arrow from rule 2.read_aloud — the whole quip as one line of respelling with the arrow after each syllable. This is the field I read off the screen, so it has to stand alone.tone_changes — which syllables come out on a different tone than the dictionary gives, and why. "" if none do.watch_out — only where this quip has a trap in it. "" otherwise; do not pad.proverb — the expression behind quip 2: the characters, the literal reading, what it actually means, and why you picked it for this. Say plainly who each half of the comparison is.tones — all five, in order, with the arrow and what to do with my voice.hard_sounds — at most five. The sounds most likely to make me unintelligible.notes — what you traded away, and which quip you expect me to lose.{ "quips": [ { "id": "fable", "chinese": "它不叫安全，叫怂。", "english": "That's not called safety. That's called being a wimp.", "joke": "The formal, corporate word 'safety' gets swapped for the bluntest slang word for cowardice. It's the Chinese equivalent of saying 'That's not caution, that's just being a chicken.' The comedy is the register drop from boardroom to playground insult.", "syllables": [ { "hanzi": "它", "say": "tah", "tone": 1, "arrow": "→" }, { "hanzi": "不", "say": "boo", "tone": 2, "arrow": "↗" }, { "hanzi": "叫", "say": "jee-YOW", "tone": 4, "arrow": "↘" }, { "hanzi": "安", "say": "ahn", "tone": 1, "arrow": "→" }, { "hanzi": "全", "say": "chwen", "tone": 2, "arrow": "↗" }, { "hanzi": "叫", "say": "jee-YOW", "tone": 4, "arrow": "↘" }, { "hanzi": "怂", "say": "sawng", "tone": 3, "arrow": "↘↗" } ], "read_aloud": "tah→ boo↗ jee-YOW↘ ahn→ chwen↗ jee-YOW↘ sawng↘↗", "tone_changes": "不 is dictionary 4th tone (falling) but becomes 2nd tone (rising) because the next syllable 叫 is also 4th tone. Written as 'boo↗' not 'boo↘'.", "watch_out": "jee-YOW is ONE syllable, not two. Say it as fast as the 'eow' in 'meow' without the m. If you say 'jee' and 'YOW' as two separate beats, Google will hear two characters and the sentence falls apart. Also: 'chwen' for 全 — round your lips as if saying 'oo' but actually say 'eh'. That lip-rounding is what separates it from 'chen'." }, { "id": "proverb", "chinese": "两个夜郎争老大。", "english": "Two Yelangs fighting to be the boss.", "joke": "Yelang was a tiny, ignorant kingdom whose king asked a Han envoy 'Which is bigger, me or your empire?' — the Chinese equivalent of a village chief asking if he outranks the Roman Emperor. Calling both superpowers 'Yelang' reduces them to the same laughable small-timer, and 'fighting to be the boss' (争老大) is the undignified phrasing you'd use for two stray dogs over a scrap.", "syllables": [ { "hanzi": "两", "say": "lyahng", "tone": 3, "arrow": "↘↗" }, { "hanzi": "个", "say": "guh", "tone": 4, "arrow": "↘" }, { "hanzi": "夜", "say": "yeh", "tone": 4, "arrow": "↘" }, { "hanzi": "郎", "say": "lahng", "tone": 2, "arrow": "↗" }, { "hanzi": "争", "say": "jung", "tone": 1, "arrow": "→" }, { "hanzi": "老", "say": "laow", "tone": 3, "arrow": "↘↗" }, { "hanzi": "大", "say": "dah", "tone": 4, "arrow": "↘" } ], "read_aloud": "lyahng↘↗ guh↘ yeh↘ lahng↗ jung→ laow↘↗ dah↘", "tone_changes": "", "watch_out": "jung (争) is NOT 'zeng' or 'zheng'. Say the 'j' in 'judge' but curl your tongue tip up and back so it almost touches the roof of your mouth. And lyahng (两) is one syllable — don't let it split into 'lee-ang'. Think of it as 'ly' + 'ahng' glued together." } ], "proverb": { "text": "夜郎自大", "literal": "Yelang aggrandizes itself", "means": "A person or entity with a laughably limited view of the world delusionally believes it is the greatest power. From the Han-dynasty story of the king of Yelang, a tiny chiefdom in modern Guizhou, who earnestly asked an imperial envoy whether his realm or the Han Empire was larger.", "why_this_one": "The US is one Yelang; China is the other. The idiom is known but sits well outside the top-30 set phrases a speaker reaches for first — most people would grab 井底之蛙 or 自不量力. 夜郎自大 is more literary, more specific, and funnier because it names an actual historical nobody. Reducing both AI superpowers to the same ignorant village chief who thinks he's the emperor is the joke. Neither gets to be the Han Empire. They're both the guy who asked the question." }, "tones": [ { "tone": 1, "arrow": "→", "what_to_do": "Sing a steady high note. Imagine holding 'la' at the top of your comfortable range. Do not let it drift up or down. Flat like a laser beam." }, { "tone": 2, "arrow": "↗", "what_to_do": "Say 'What?' when you didn't hear someone. Start mid-pitch, slide up. It's a question, but you're not asking one — just borrow that upward contour." }, { "tone": 3, "arrow": "↘↗", "what_to_do": "Say 'Well…' when you're skeptical and drawing it out. Your pitch dips down into your chest and then climbs back up. It's the longest tone; give it time." }, { "tone": 4, "arrow": "↘", "what_to_do": "Say 'No!' firmly, or 'Stop!' Start high and chop downward. It's short and aggressive, like slamming a book shut." }, { "tone": 0, "arrow": "·", "what_to_do": "Short, light, no pitch contour. Like the 'a' in 'about' or the 'uh' in 'the'. Just a quick, unstressed grunt. Neither quip uses this, but it exists." } ], "hard_sounds": [ { "sound": "jee-YOW (叫 jiào)", "what_to_do": "The 'j' is like 'jeep' but press your tongue tip down behind your bottom teeth instead of the ridge behind your top teeth. Then glide straight into 'YOW' (rhymes with 'cow'). The whole thing is one syllable: jee-YOW, as fast as 'meow' minus the m." }, { "sound": "chwen (全 quán)", "what_to_do": "Say 'ch' as in 'cheese' but flatten your tongue: the blade of your tongue touches the roof of your mouth, not the tip. Then say 'wen' with rounded lips, as if you're about to whistle. It's 'ch' + 'wen' with lip-rounding on the 'w'." }, { "sound": "jung (争 zhēng)", "what_to_do": "Say the 'j' in 'judge' but curl your tongue tip upward and backward until it nearly touches the bumpy ridge on the roof of your mouth. Then add 'ung' as in 'lung'. The tongue-curl is what makes it 争 instead of 曾." }, { "sound": "lyahng (两 liǎng)", "what_to_do": "This is one syllable, not 'lee-ang'. Start with 'l', then your mouth opens wide into 'yahng' (rhymes with 'song' but with an 'ah' vowel). Think of saying 'lion' but replacing the 'on' with 'ahng'. Keep it glued: lyahng." }, { "sound": "sawng (怂 sǒng)", "what_to_do": "The 's' is normal English 's'. The vowel is 'aw' as in 'saw'. End with 'ng' as in 'song'. The danger is the 3rd tone: you must dip your pitch down and back up, not just say it low. Think 'SAAW-ng' with your voice scooping down then up." } ], "notes": "Trade-off on Quip 1: I kept 怂 (sǒng, 'wimp') instead of the easier-to-pronounce 胆小 (dǎnxiǎo, 'timid'). 怂 is funnier because it's one blunt syllable and slightly vulgar — it's the word you'd use about a friend who won't ask someone out. 胆小 would sound like a medical chart. You're paying for that extra comedy with a 3rd-tone 'sawng' that English speakers tend to flatten. I expect Quip 1 to be the one you lose on the Google voice-input test, specifically at 'jee-YOW' and 'chwen'. If you get three out of seven syllables recognized, that's a win. Quip 2 is phonetically friendlier — no q, x, or j-initials, and the vowels are all ones English has. You should land most of it. If you have to sacrifice rehearsal time, spend it on Quip 1's 'jee-YOW' and 'chwen'." }