Baidu Text-to-Speech vs Orpheus TTS
Baidu Text-to-Speech
cloud.baidu.comOrpheus TTS
github.comSide by side
| Figure | Baidu Text-to-Speech | Orpheus TTS |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | — |
| Linux | Yes | — |
| iOS | Yes | — |
| Android | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 14 | 0 |
| Spec score · Text-to-Speech Software | 9.3 (#3) | 7.4 (#171) |
| Spec score · Text-to-speech tools | 9.3 (#5) | 7.4 (#183) |
| API access | Yes | Yes |
| Export formats | mp3,pcm,wav | WAV |
| Headquarters | Beijing, China | San Francisco, California, United States |
| Platforms | web,api,ios,android,linux | api,self_hosted |
| Purpose | Converts text into natural-sounding speech for applications and devices. | Orpheus TTS is an open-source text-to-speech system built on a Llama 3B backbone. |
| Streaming | Streaming synthesis supports bidirectional text and speech so synthesized audio can be heard nearly as text is entered. | The repository reports about 200 ms streaming latency, reducible to about 100 ms with input streaming. |
| Voice cloning | Yes | The project lists zero-shot voice cloning without prior fine-tuning as an ability. |
Plans
Baidu Text-to-Speech
- Short-text Basic Voice LibraryPrice not published
- Short-text Premium Voice LibraryPrice not published
- Short-text Large-model and Premium Voice LibraryPrice not published
- Long-text Basic Voice LibraryPrice not published
- Long-text Premium Voice LibraryPrice not published
- Long-text Large-model and Premium Voice LibraryPrice not published
- Streaming Basic Voice LibraryPrice not published
- Streaming Premium Voice LibraryPrice not published
- Streaming Large-model and Premium Voice LibraryPrice not published
- 离线语音合成试用版Free
In their own words
Baidu Text-to-Speech
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.
Orpheus TTS
Orpheus TTS has no write-up on Specifiction yet; its figures are above.