Hearing Loss (HL) is the most prevalent sensorineural disorder, affecting 360 million people worldwide. As genetic causes lead to 50% of pre-lingual deafness, gene therapy is considered as a potential therapeutic strategy. Mutations in the TMC1 gene are linked to both autosomal dominant (DFNA36) and recessive (DFNB7/11) forms of non-syndromic HL. DFNA36 is caused by a TMC1 point mutation (p.M418K) and characterized by a postlingual form of HL, with an onset in the mid-teen years, which leaves a window for therapeutic intervention. The natural disease progression is replicated in the heterozygous Tmc1Bth/+ Beethoven mice, a useful model for the testing of gene therapies. Here, we develop an AAV-based allele-specific gene targeting approach using the CRISPR/Cas9 technology to selectively disrupt and knock-out the Bth-Tmc1 allele. To deliver this system to the neonatal inner ear, we used the AAV-PHP.B vector, which showed effective targeting of both inner and outer hair cells throughout the mouse cochlea (>90% efficacy). This transduction efficacy allowed us to consider a double vector approach, with one vector used to express the spCas9 nuclease whereas a second vector was co-injected to express the gRNA selectively targeting the Bth-Tmc1 allele. The results obtained in the Tmc1Bth/+ mice showed long-lasting improvement of the auditory function, with a significant protection of the auditory brainstem response and the distortion product otoacoustic emissions. Furthermore, the treated mice showed a significantly increased startle reflex response. Altogether, these results support the use of AAV-based gene therapy to target genetic defects in hair cells leading to HL.