Audio Hub › Text-to-speech

DiffSinger

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Category

Text-to-speech

Type

Open source

Platform

Python project

Pricing

Free / open source

License

MIT

GitHub stars

4,844

Last updated

2026-07-24

GitHub repo →

Top DiffSinger alternatives

ElevenLabsState-of-the-art AI voices: cloning, dubbing and long-form narration with an API developers build on.Murf AIStudio-style AI voiceover tool with 120+ voices, pitch/speed control and sync-to-video for explainer content.PlayHTAI voice generation with a large voice library, voice cloning and a real-time streaming API.WellSaidEnterprise-leaning AI voiceover with consistent branded voices and team workflows for e-learning and product content.SpeechifyRead-aloud app that turns articles, PDFs and books into natural speech; popular for accessibility and study.NaturalReaderLong-standing text-to-speech tool for documents and web pages with commercial-license voices on paid tiers.

See the full list of DiffSinger alternatives →