🎙️ Kokoro TTS
v1.1.0
📄 Swagger
📚 ReDoc
GPU
Single
Stream
WebSocket
Batch
📝 Text to Speech
Kokoro is an open-weight TTS model with 82 million parameters.
Model
Voice
Speed:
1.0
x
🎵 Generate
📡 Streaming TTS
This is the first sentence for streaming. This is the second sentence. And this is the third sentence. The audio will play as each sentence generates.
Model
Voice
Speed:
1.0
x
📡 Start Stream
⏹ Stop
首字节延迟
-
开始播放
-
总时间
-
数据大小
-
🔌 WebSocket TTS
Disconnected
Hello via WebSocket! Real-time bidirectional communication.
Model
Voice
Speed:
1.0
x
🔗 Connect
📤 Send
❌ Disconnect
📦 Batch Processing
[{"id":"1","text":"Hello world","voice":"af_heart"},{"id":"2","text":"Goodbye","voice":"am_michael"}]
Model
Default Voice
Default Speed:
1.0
x
🚀 Process Batch
▶️ Play All
💾 Download All
⚡ Status
Release
Device
-
Memory
-
Model
-
🎤 Voices