diff --git a/go/README.md b/go/README.md
index bdaa6b3..b2708a0 100644
--- a/go/README.md
+++ b/go/README.md
@@ -138,6 +138,7 @@ This will:
 | `-use-gpu` | flag | false | Use GPU for inference (default: CPU) |
 | `-onnx-dir` | str | `../assets/onnx` | Path to ONNX model directory |
 | `-total-step` | int | 8 | Number of denoising steps (higher = better quality, slower) |
+| `-speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
 | `-n-test` | int | 4 | Number of times to generate each sample |
 | `-voice-style` | str | `../assets/voice_styles/M1.json` | Voice style file path(s), comma-separated |
 | `-text` | str | (long default text) | Text(s) to synthesize, pipe-separated |
diff --git a/java/README.md b/java/README.md
index e6561f9..df92ff5 100644
--- a/java/README.md
+++ b/java/README.md
@@ -120,6 +120,7 @@ java -jar target/tts-example.jar --total-step 10 --text "Your custom text here"
 | `--use-gpu` | flag | False | Use GPU for inference (default: CPU) |
 | `--onnx-dir` | str | `../assets/onnx` | Path to ONNX model directory |
 | `--total-step` | int | 8 | Number of denoising steps (higher = better quality, slower) |
+| `--speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
 | `--n-test` | int | 4 | Number of times to generate each sample |
 | `--voice-style` | str+ | `../assets/voice_styles/M1.json` | Voice style file path(s), comma-separated |
 | `--text` | str+ | (long default text) | Text(s) to synthesize, pipe-separated |
diff --git a/rust/README.md b/rust/README.md
index 233474f..efc6073 100644
--- a/rust/README.md
+++ b/rust/README.md
@@ -127,6 +127,7 @@ This will:
 | `--use-gpu` | flag | False | Use GPU for inference (default: CPU) |
 | `--onnx-dir` | str | `../assets/onnx` | Path to ONNX model directory |
 | `--total-step` | int | 8 | Number of denoising steps (higher = better quality, slower) |
+| `--speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
 | `--n-test` | int | 4 | Number of times to generate each sample |
 | `--voice-style` | str+ | `../assets/voice_styles/M1.json` | Voice style file path(s), comma-separated |
 | `--text` | str+ | (long default text) | Text(s) to synthesize, pipe-separated |
diff --git a/swift/README.md b/swift/README.md
index d674420..51b0558 100644
--- a/swift/README.md
+++ b/swift/README.md
@@ -97,6 +97,7 @@ This will:
 | `--use-gpu` | flag | False | Use GPU for inference (default: CPU) |
 | `--onnx-dir` | str | `../assets/onnx` | Path to ONNX model directory |
 | `--total-step` | int | 8 | Number of denoising steps (higher = better quality, slower) |
+| `--speed` | float | 1.05 | Speech speed factor (higher = faster, lower = slower) |
 | `--n-test` | int | 4 | Number of times to generate each sample |
 | `--voice-style` | str+ | `../assets/voice_styles/M1.json` | Voice style file path(s) |
 | `--text` | str+ | (long default text) | Text(s) to synthesize |