F5-TTS

MIT flow-matching TTS with expressive multilingual voices at consumer-GPU speed.

Install Repository Website Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 8 GB
Gpu: Optional · 6 GB VRAM helps
Docker: No
Setup: Intermediate
Deploy as: Local
Commercial use: Allowed

Fine as CPU inference, but a 6 GB GPU makes it pleasant.

Project.

Fetched Sep 12, 2026¹

License: MIT
Stars: 15.2k¹
Forks: 2.2k¹
Open issues: 49¹
Language: Python¹
Last commit: Jul 23, 2026¹
Tags: ttsflow-matchingmultilingual

About.

F5-TTS is an MIT flow-matching voice model with natural prosody, fast inference, and strong multilingual coverage. The HuggingFace Space made it the default open narration engine. Runs on 6 GB VRAM or patient CPU.

flow-matching TTS · speed control · 28-language support · voice conversion

Alternatives.

Nearby.

All Speech AI

WWhisperOpenAI’s speech-to-text model you can run locally.Compare
PPiperFast local neural text-to-speech that runs on CPU.Compare
Wwhisper.cppC/C++ port of Whisper for fast local transcription.Compare
FFaster-WhisperWhisper reimplementation on CTranslate2 for faster local ASR.Compare
WwhisperXWhisper with word-level timestamps and speaker diarization for real subtitles.Compare