Baidu Text-to-Speech vs VoiceStudio

Baidu Text-to-Speech converts text into speech for applications and devices, with Chinese, English, mixed Chinese-English, and more than 70 voice styles available through its online service. Users can change speech rate, pitch, volume, and supported emotional effects; Chinese polyphonic characters can be annotated with pronunciation. Streaming synthesis can play audio nearly as text is entered, and long-text synthesis handles up to 100,000 Chinese characters in one request. Baidu provides HTTP and WebSocket APIs, online and offline SDKs, and Android and iOS SDKs for phones and smart devices. Offline synthesis is intended for settings with weak or no network access, including mobile apps, readers, robots, and smart hardware. Listed uses include audiobook reading, news and order announcements, and smart hardware. Short-text API requests must stay under 1,024 GBK bytes, with 120 bytes or less recommended. Export formats are MP3, PCM, and WAV. The service offers a free trial; offline trial and license plans are listed, while prices for other listed plans are not provided.

VoiceStudio is an open-source voice AI studio for local voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation. Users can describe a voice by gender, age, accent, pitch and emotion without providing reference audio. Its dubbing workflow transcribes and translates video, then re-voices it while keeping speakers separate and aligning timing with the original. Users can create multi-voice audio from scripts and chaptered audiobooks from long text or EPUB files. The desktop app exposes a local OpenAI-compatible API for speech, voices, transcription and dubbing. The maker lists 26 adapters, including local text-to-speech and transcription engines and a configured-remote ASR adapter. The maker says recordings, generated audio, transcripts and derived voice data stay on user-controlled storage and are not received by its website or control plane. The app may access the network for updates, model downloads or explicitly network-backed adapters. The public build has no hosted dashboard or Cloud API. Open Source costs nothing under AGPL-3.0; Pro costs $99 a year and Lifetime costs $299, paid once. Speech model licences are separate.