BreezeVoice is a Windows text to speech software that allows users to input text, select services and tones, export audio and SRT subtitles. Connect Edge, Azure, Alibaba Cloud Bailian, ElevenLabs, and Windows system voice in one window, with unified adjustment of speech rate, tone, and volume, without the need to switch back and forth between several backends.

1. Five voice services, with sound filtering by language and gender, available for trial listening and bookmarking
2. Insert pauses and specify the pronunciation of polyphonic characters
3. Long articles are automatically segmented and synthesized to form a complete file
4. Batch generation and multi role dialogue
5. Export MP3/WAV and generate SRT subtitles simultaneously
6. Import text from txt, Word (. docx), and SRT subtitles

Five voice services, one window

Edge and system voice do not require any account; Azure、 Alibaba Cloud Bailian and ElevenLabs need to fill in your own API Key in the settings, and the fees will be settled according to each company's rules. The API key is saved in the Windows credential manager and is not written to any file.

1. Edge Online:Key free, ready to use out of the box; Subtitle timeline precise to sentence (unofficial interface from Microsoft)
2. Azure Voice:Microsoft official service, with free files available; Pronunciation correction using SSML phonetics
3. Alibaba Cloud Bailian:CosyVoice Chinese tone, adjustable speed, pitch, and volume
4. ElevenLabs：Support emotional tags, allowing users to directly select cloned tones already available in their account
5. Windows system voice:Can be used even without internet connection, with average sound quality, suitable for emergency situations

Features

1. Insert pauses and correct homophones

Insert a specified duration of pause in the text, and all services will have the same effect. The subtitle time will be automatically extended. Polyphones can be manually pronounced, such as' x í ng 'and' h á ng '.

1. Automatic segmentation of long text

The entire article is directly pasted in, and the software cuts and synthesizes each sentence segment without loss, and then assembles them into a complete file. The bottom progress bar displays segmented progress, which can be cancelled midway.

1. batch generate

Split by line, by blank line, or by file, each generating an independent audio. A single failure does not affect other attempts and can be attempted separately.

1. Multi role dialogue

Assign a character to each sentence, and each character is bound to their own service and tone. Synthesize sentence by sentence, leave blank spaces between sentences, and finally export a complete audio and a subtitle.

1. Tone Director

Describe the desired tone in one sentence, such as "calm down first, speak slowly, then speed up and finish angrily", and have the big model cut the dialogue into several segments and mark the pace and emotion. Choose from Alibaba Cloud Bailian, DeepSeek, Kimi, OpenAI, or self filling interfaces.

1. MP3/WAV+SRT subtitles

Export MP3 or WAV while generating SRT subtitles. The sentence time returned by Edge through the interface is precise on the timeline; Other services are estimated by word count and marked next to it as "accurate" or "estimated".

Free version and Pro: The free version can use single segment dubbing and generate up to 10 times a day; After activating Pro, unlock batch generation and multi character conversations without limit on the number of times.

Target Audience

1. Short video dubbing
2. Course and instructional videos
3. Production of audio content
4. Subtitle group and translation
5. Advertising and promotional video samples
6. Batch production prompt sound