STATE is a multimodal assisted transcription tool for document processing and text transcription. It comprises a graphical front-end that can be easily connected to different text recognition back-ends. We present here the front-end and two back-ends: one based on nearest neighbors (for ancient printed text) and one based on hybrid HMM/ANN models (for unconstrained handwritten text). Experimentation shows that if the back-end has a moderately low character error rate, productivity gains can be as high as 100% when compared to directly transcribing the text.