Sounds like premature optimization. Unless you have a problem with performance, I'd go with JSON.stringify, no extra code to write, no need to figure out how to encode it.
None of the answers here are good enough, since they don't encode all the possible things like \n, \r, \t or quotes
Here's a blatant copy of the code from json.org that does what you need. http://jsfiddle.net/mendesjuan/rFCwF/
function quote(string) {
var escapable = /[\\\"\x00-\x1f\x7f-\x9f\u00ad\u0600-\u0604\u070f\u17b4\u17b5\u200c-\u200f\u2028-\u202f\u2060-\u206f\ufeff\ufff0-\uffff]/g;
var meta = { // table of character substitutions
'\b': '\\b',
'\t': '\\t',
'\n': '\\n',
'\f': '\\f',
'\r': '\\r',
'"' : '\\"',
'\\': '\\\\'
}
// If the string contains no control characters, no quote characters, and no
// backslash characters, then we can safely slap some quotes around it.
// Otherwise we must also replace the offending characters with safe escape
// sequences.
escapable.lastIndex = 0;
return escapable.test(string) ? '"' + string.replace(escapable, function (a) {
var c = meta[a];
return typeof c === 'string' ? c :
'\\u' + ('0000' + a.charCodeAt(0).toString(16)).slice(-4);
}) + '"' : '"' + string + '"';
}