f5-tts

library1.1.20pypypiunverified

F5-TTS is a text-to-speech library using flow matching, designed for faithful and fluent speech synthesis. Current version: 1.1.20. Active development with frequent releases.

ai-ml llm-agents

pip install f5-tts

github ↗package ↗

INSTALL

IMPORT

SIG · F5-TTS

f5-tts

ai-mlpythonv1.1.20

Install

109.4s avg

Import

—

Disk

6349MB

Pass rate

1/ 10

Env Coverage1 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.1.20 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✕ timeout

py 3.11

✕ build_error

✕ timeout

py 3.12

✕ build_error

✕ timeout

py 3.13

✕ build_error

✓ 109.4s

py 3.9

✕ build_error

✕ timeout

6349MB installed

● package 6349MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

F5TTS

✓ from f5_tts import F5TTS

✗ from f5_tts import F5TTS

Quick start for basic inference with a reference audio clip.

from f5_tts import F5TTS tts = F5TTS() # Generate speech from text waveform, sample_rate = tts.infer(text="Hello, world!", ref_audio="path/to/ref.wav", ref_text="Reference text") # Save to file import soundfile as sf sf.write("output.wav", waveform, sample_rate)

Debug

Known issues

gotchaGradio version conflict: Gradio >=6.11 causes UI freeze. Pin to <6.11 or use version from requirements.

fix

pip install 'gradio<6.11'

affects: >=1.1.20

deprecatedDirect import of model classes (e.g., `from f5_tts.model import F5TTS`) may break in future releases. Use top-level `from f5_tts import F5TTS`.

fix

from f5_tts import F5TTS

affects: >=1.1.0

gotchaInference requires both reference audio and reference text. Omitting ref_text may yield poor quality.

fix

Always provide matching reference text for best results.

affects: all

Upgrade

Version history

1.1.20latest on PyPI · released Apr 20, 2026

Audit

Dependencies

torchrequiredCore requirement for model execution

gradiooptionalInference UI, version <6.11 recommended

vocosoptionalVocoder for waveform generation

Agent activity

20 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/SWivid/F5-TTS ↗

packagehttps://pypi.org/project/f5-tts/ ↗