bailian-cli 0.1.0 → 0.1.2-beta.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -62,8 +62,8 @@ bl video generate --image ./cat.png --prompt "Make the cat move" --download cat.
62
62
  | **Omni** | `omni` (text+image+audio+video) | qwen3.5-omni-plus |
63
63
  | **Image** | `image generate` | qwen-image-2.0 |
64
64
  | | `image edit` (multi-image merge) | qwen-image-2.0 |
65
- | **Video** | `video generate` (text/image-to-video) | wan2.7-t2v / wan2.7-i2v |
66
- | | `video edit` (style transfer) | wan2.7-videoedit |
65
+ | **Video** | `video generate` (text/image-to-video) | happyhorse-1.0-t2v / happyhorse-1.0-i2v |
66
+ | | `video edit` (style transfer) | happyhorse-1.0-video-edit |
67
67
  | | `video task get` / `video download` | — |
68
68
 
69
69
  </td></tr>
@@ -72,8 +72,8 @@ bl video generate --image ./cat.png --prompt "Make the cat move" --download cat.
72
72
  | Category | Commands | Default Model |
73
73
  |:---------|:---------|:--------------|
74
74
  | **Vision** | `vision describe` | qwen-vl-max |
75
- | **Speech** | `speech synthesize` (TTS) | qwen3-tts-flash |
76
- | | `speech recognize` (ASR) | qwen3-asr-flash |
75
+ | **Speech** | `speech synthesize` (TTS) | cosyvoice-v3-flash |
76
+ | | `speech recognize` (ASR) | fun-asr |
77
77
  | **File** | `file upload` (to temp OSS) | — |
78
78
  | **App** | `app call` (agents / workflows) | — |
79
79
  | **Memory** | `memory add/search/list/update/delete` | — |
@@ -146,11 +146,14 @@ bl video edit --video ./input.mp4 --prompt "Convert to clay style"
146
146
  ### Speech
147
147
 
148
148
  ```bash
149
+ # List available voices
150
+ bl speech synthesize --list-voices --model cosyvoice-v3-flash
151
+
149
152
  # Text-to-speech
150
- bl speech synthesize --text "Hello world" --voice Serena --out speech.wav
153
+ bl speech synthesize --text "Hello world" --voice longyumi_v3 --out speech.wav
151
154
 
152
155
  # Stream to audio player (macOS)
153
- bl speech synthesize --text "你好" --stream | afplay -
156
+ bl speech synthesize --text "你好" --voice longyumi_v3 --stream | afplay -
154
157
 
155
158
  # Speech-to-text (local file auto-uploaded)
156
159
  bl speech recognize --url ./meeting.mp3