src/f5_tts/infer/examples/multi/story.toml

# F5TTS_v1_Base | E2TTS_Base
model = "F5TTS_v1_Base"
ref_audio = "infer/examples/multi/main.flac"
# If an empty "", transcribes the reference audio automatically.
ref_text = ""
gen_text = ""
# File with text to generate. Ignores the text above.
gen_file = "infer/examples/multi/story.txt"
remove_silence = true
output_dir = "tests"
output_file = "infer_cli_story.wav"

[voices.town]
ref_audio = "infer/examples/multi/town.flac"
ref_text = ""

[voices.country]
ref_audio = "infer/examples/multi/country.flac"
ref_text = ""