Estou usando a API com este código:

NSArray *paths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES);
NSString *documentsDirectory = [paths objectAtIndex:0];
NSString *path = [documentsDirectory stringByAppendingPathComponent:@"file.mp3"];

NSString *text = textToTranslate; //@"You are one chromosome away from being a potato.";
NSString *urlString = [NSString stringWithFormat:@"http://www.translate.google.com/translate_tts?tl=en&q=%@",text];
NSURL *url = [NSURL URLWithString:[urlString stringByAddingPercentEscapesUsingEncoding:NSUTF8StringEncoding]];
NSMutableURLRequest* request = [[NSMutableURLRequest alloc] initWithURL:url] ;
[request setValue:@"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1" forHTTPHeaderField:@"User-Agent"];
NSURLResponse* response = nil;
NSError* error = nil;
NSData* data = [NSURLConnection sendSynchronousRequest:request
                                     returningResponse:&response
                                                 error:&error];
[data writeToFile:path atomically:YES];

SystemSoundID soundID;
NSURL *url2 = [NSURL fileURLWithPath:path];

AudioServicesCreateSystemSoundID((__bridge CFURLRef)url2, &soundID);
AudioServicesPlaySystemSound (soundID);

Que funciona, mas apenas em frases curtas (menos de 10 palavras aprox.) O que estou fazendo errado? Como posso resolver isso ou separar em poucos textos sem reduzir a qualidade da fala?