Back: Catalog

F5-TTS

F5-TTS is a text-to-sound (TTS) conversion software that uses flow matching and ConvNeXt V2-based Diffusion Transformer architecture. The project includes the Sway Sampling strategy for E2 TTS support and flow step sampling. It runs in a Python and PyTorch based environment, can be installed as a package by pip, or cloned for local development.

F5

F5-TTS

100

SWivid · AI Call Agents & Telephony

STARS15.5K
FORKS2.3K
COMMITS685
CONTRIBUTORS63
VERSION1.1.9
UPDATED7 days ago
PythonFlow MatchingZero-Shot KlonlamaTürkçeMIT

Common commercial products in this category: Vapi, Bland AI, Retell AI

What can it do?
  • By giving a reference audio recording and text, you convert the text from the command line or from the Gradio interface into that voice speech.
  • By cloning the local source code, you can perform model training and fine-tuning.
  • Using Docker, you can run the application in a container environment.
Website GitHub

Verified against README · Oct 25, 2026 · source

My note

Alternative pages

Vapi alternativesBland AI alternativesRetell AI alternatives

More in: AI Call Agents & Telephony