[package] name = "indextts" version = "0.1.0" edition = "2021" description = "High-performance Text-to-Speech engine in pure Rust - converted from IndexTTS Python" authors = ["IndexTTS Team"] license = "MIT" keywords = ["tts", "speech-synthesis", "audio", "ml", "deep-learning"] categories = ["multimedia::audio", "science"] [[bin]] name = "indextts" path = "src/main.rs" [lib] name = "indextts" path = "src/lib.rs" [dependencies] # Core ML/Inference ort = { version = "2.0.0-rc.4", features = ["load-dynamic"] } safetensors = "0.4" ndarray = { version = "0.15", features = ["rayon"] } # Audio Processing hound = "3.5" dasp_signal = "0.11" dasp_sample = "0.11" rustfft = "6.2" realfft = "3.3" rubato = "0.15" # Text Processing tokenizers = "0.19" unicode-segmentation = "1.11" regex = "1.10" lazy_static = "1.5" jieba-rs = "0.7" # CLI & Configuration clap = { version = "4.5", features = ["derive"] } serde = { version = "1.0", features = ["derive"] } serde_json = "1.0" serde_yaml = "0.9" toml = "0.8" config = "0.14" # Async & Parallelism rayon = "1.10" tokio = { version = "1.38", features = ["full"] } # Utilities anyhow = "1.0" thiserror = "1.0" log = "0.4" env_logger = "0.11" indicatif = "0.17" bytemuck = { version = "1.16", features = ["derive"] } num-complex = "0.4" num-traits = "0.2" rand = "0.8" num_cpus = "1.16" # HTTP/Download reqwest = { version = "0.12", features = ["blocking", "json"] } sha2 = "0.10" hex = "0.4" [dev-dependencies] criterion = "0.5" tempfile = "3.10" [profile.release] opt-level = 3 lto = true codegen-units = 1 strip = true [profile.dev] opt-level = 1 [[bench]] name = "mel_spectrogram" harness = false [[bench]] name = "inference" harness = false