文字转语音 语音转文字 视频识别字幕
Loading..
Loading...
文字转语音MP3是一款文字转语音软件，可以将文字转换为MP3声音文件，也可以将语音转换成文字和字幕文件。基于讯飞语音和阿里云智能语音合成以及腾讯语音识别技术开发而成。
可用来制作超市店铺促销声音文件、地摊叫卖清仓大甩卖广告录音、影视配音、小说音频、电子书文档朗读、英文听力音频等。语音识别出文字和SRT字幕则可以用于识别出录音文件，提高工作效率。
用户可以到设置中切换不同发音人和设置音量、语速和语调。普通发音人5人，仅支持中文普通话。精品发音人20人，支持中文普通话、英语和粤语。
【核心功能】
1.智能语音合成，核心技术由讯飞语音和阿里云智能语音合成提供。
2.导出MP3文件，生成的MP3文件可以分享到电脑播放。
3.智能语音识别，录音文件识别出文字并导出文本文件。
4.短视频识别出字幕并导出SRT字幕文件。
5.将合成的文字语音和背景音乐进行混音。
6.将多个合成的语音进行合并，或者和其它音乐进行合并。
【适用场景】
1.广告配音：商场广告促销、地摊叫卖、企业宣传、影视配音等。
2.有声阅读：小说、杂志、课本、通话等文字轻松转成MP3文件。
3.视频字幕生成，语音资料转写等场景。
4.英语读物：制作英语配音。
【资费说明】
1.普通文字转语音MP3服务不收取任何费用，但合成效果不如精品发音人。
2.精品文字转语音MP3按照每250字0.1元收费，比如合成1000个汉字收费为0.4元。
3.语音转文字和字幕按照每2分钟0.1元收费，建议视频不超过25分钟或音频数据不能大于5MB。
Text-to-speech MP3 is a text-to-speech software that can convert text to MP3 sound files as well as voice to text and subtitle files. Developed based on Xunfei Voice and Alibaba Cloud intelligent speech synthesis and Tencent speech recognition technology.
It can be used to produce promotional sound files for supermarket stores advertising recordings of stall sales and clearance sales movie dubbing novel audio e-book document reading English listening audio etc. Speech recognition text and SRT subtitles can be used to identify recorded files improving work efficiency.
Users can switch to different speakers in the settings and set the volume speed and intonation. There are 5 ordinary speakers and only Chinese Mandarin is supported. There are 20 native speakers supporting Chinese Mandarin English and Cantonese.
【Core functions】
1. Intelligent speech synthesis. The core technology is provided by Xunfei Speech and Alibaba Cloud Intelligent Speech Synthesis.
2. Export the MP3 file the generated MP3 file can be shared to the computer for playback.
3. Intelligent speech recognition recording files recognize text and export text files.
4. Short videos recognize subtitles and export SRT subtitle files.
5. Mix the synthesized text speech and background music.
6. Combine multiple synthesized voices or merge with other music.
【Applicable scene】
1. Advertising dubbing: shopping mall advertising promotions stall sales corporate publicity film dubbing etc.
2. Audio reading: Novels magazines textbooks phone calls etc. are easily converted into MP3 files.
3. Video subtitle generation voice data transcoding and other scenarios.
4. English books: Produce English dubbing.
[Tariff Description]
1. The ordinary text-to-speech MP3 service does not charge any fees but the synthesis effect is not as good as that of a good speaker.
2. The premium text-to-speech MP3 is charged at 0.1 yuan per 250 words for example the charge for synthesizing 1000 Chinese characters is 0.4 yuan.
3. Voice-to-text and subtitles are charged at 0.1 yuan per 2 minutes. It is recommended that the video does not exceed 25 minutes or the audio data cannot be larger than 5MB.
可用来制作超市店铺促销声音文件、地摊叫卖清仓大甩卖广告录音、影视配音、小说音频、电子书文档朗读、英文听力音频等。语音识别出文字和SRT字幕则可以用于识别出录音文件，提高工作效率。
用户可以到设置中切换不同发音人和设置音量、语速和语调。普通发音人5人，仅支持中文普通话。精品发音人20人，支持中文普通话、英语和粤语。
【核心功能】
1.智能语音合成，核心技术由讯飞语音和阿里云智能语音合成提供。
2.导出MP3文件，生成的MP3文件可以分享到电脑播放。
3.智能语音识别，录音文件识别出文字并导出文本文件。
4.短视频识别出字幕并导出SRT字幕文件。
5.将合成的文字语音和背景音乐进行混音。
6.将多个合成的语音进行合并，或者和其它音乐进行合并。
【适用场景】
1.广告配音：商场广告促销、地摊叫卖、企业宣传、影视配音等。
2.有声阅读：小说、杂志、课本、通话等文字轻松转成MP3文件。
3.视频字幕生成，语音资料转写等场景。
4.英语读物：制作英语配音。
【资费说明】
1.普通文字转语音MP3服务不收取任何费用，但合成效果不如精品发音人。
2.精品文字转语音MP3按照每250字0.1元收费，比如合成1000个汉字收费为0.4元。
3.语音转文字和字幕按照每2分钟0.1元收费，建议视频不超过25分钟或音频数据不能大于5MB。
Text-to-speech MP3 is a text-to-speech software that can convert text to MP3 sound files as well as voice to text and subtitle files. Developed based on Xunfei Voice and Alibaba Cloud intelligent speech synthesis and Tencent speech recognition technology.
It can be used to produce promotional sound files for supermarket stores advertising recordings of stall sales and clearance sales movie dubbing novel audio e-book document reading English listening audio etc. Speech recognition text and SRT subtitles can be used to identify recorded files improving work efficiency.
Users can switch to different speakers in the settings and set the volume speed and intonation. There are 5 ordinary speakers and only Chinese Mandarin is supported. There are 20 native speakers supporting Chinese Mandarin English and Cantonese.
【Core functions】
1. Intelligent speech synthesis. The core technology is provided by Xunfei Speech and Alibaba Cloud Intelligent Speech Synthesis.
2. Export the MP3 file the generated MP3 file can be shared to the computer for playback.
3. Intelligent speech recognition recording files recognize text and export text files.
4. Short videos recognize subtitles and export SRT subtitle files.
5. Mix the synthesized text speech and background music.
6. Combine multiple synthesized voices or merge with other music.
【Applicable scene】
1. Advertising dubbing: shopping mall advertising promotions stall sales corporate publicity film dubbing etc.
2. Audio reading: Novels magazines textbooks phone calls etc. are easily converted into MP3 files.
3. Video subtitle generation voice data transcoding and other scenarios.
4. English books: Produce English dubbing.
[Tariff Description]
1. The ordinary text-to-speech MP3 service does not charge any fees but the synthesis effect is not as good as that of a good speaker.
2. The premium text-to-speech MP3 is charged at 0.1 yuan per 250 words for example the charge for synthesizing 1000 Chinese characters is 0.4 yuan.
3. Voice-to-text and subtitles are charged at 0.1 yuan per 2 minutes. It is recommended that the video does not exceed 25 minutes or the audio data cannot be larger than 5MB.
Show More >
