Product introduction:
SONIC PROSnick Audio has implanted into the industry's leading core voice engine, and combined our many years of experience in conference occasions to develop a software and hardware combination to realize real-time voice transcription, meeting recording, and audio recording. This voice transcription processor adopts offline privatization deployment and uses core voice recognition transcription technology. Speech clarity standards Chinese Mandarin transcription accuracy, and high.97%, also supports English transcriptions, and the accuracy rate of English transcriptions is up to93%In meeting occasions under the application of Snick Audio and Speech Processor, it can help users solve the problem of real-time conversion of on-site amplified speech and played audio files into text during the meeting, and can form horse racing subtitles and put them on the screen to assist meeting recorders. Organize and correct the meeting minutes, and the functions such as modal particle filtering and automatic segmentation provided by the system automatically optimize the text results to achieve rapid completion. It is especially suitable for domestic enterprises and institutions, education, training, live broadcast of programs and other conference speeches, conference discussions, communication, large-scale conferences and a series of scenarios with meeting records, voice transcriptions, and audio recording requirements.
Product features:
Multiple dialects: In addition to Mandarin, there are also Cantonese, Sichuan dialect, Henan dialect, Northeast dialect, Tianjin dialect, Hunan dialect, Jinan dialect, Shandong dialect, Wuhan dialect, Hefei dialect, Jiangxi dialect, Minnan dialect, Shaanxi Xi'an dialect, Nanjing dialect, Shanxi Taiyuan dialect, Shanghai dialect, Guizhou dialect, Hakka dialect, Yunnan Kunming dialect, Hebei dialect, Gansu dialect, Ningxia dialect, Northern Anhui dialect, Taiwanese dialect, Suzhou dialect, etc.24Two dialects are available to choose from.
Subtitle superposition, the voice transcription processor transcribes text to achieve subtitle superposition on videos and documents in the conference. The voice transcription processor comes with it.1Road support1080PHDHDMIVideo input port,1Road support1080PHDHDMIVideo output port, device supportRTSPThe video stream achieves local subtitles superimposed through internal processing, so that the voice transcription results are superimposed on the picture in the form of horse racing subtitles.
For post-editing, the voice transcription results stored in the form of documents in the voice transcription processor storage solid state drive can be downloaded and proofread, edited, and modified with the recording files to ensure dual backup of audio and text of important meeting content.
Basic parameters:
Mode dialing code:1group4DIPcode dialing device;
Reset button:11 reset button with aperture system;
Power interface:1aDC 12VPower adapter power supply port;
Body material: All aluminum alloy chassis
frequency response(20～20kHz)： ±0.2dB
total harmonic distortion(THD+N)：0.002% @1kHz，+4dBu
Output impedance: 100 Ω balance，50 unbalance
Operating temperature: 0~40℃
size(widexdeepxhigh) ：482×262×44mm
Product weight:2.22kg
