Hawk Lee
eff537d9dd
- Add AIIA_ASR node with FunASR (paraformer-zh + SenseVoiceSmall) - Add AIIA_Podcast_Splitter for per-speaker text splitting - Add AIIA_Podcast_Stitcher with 3-tier fuzzy alignment (exact, Levenshtein, fallback) - Register 5 previously missing modules in __init__.py - Update README with installation guide and node documentation
43 lines
757 B
Protocol Buffer
43 lines
757 B
Protocol Buffer
syntax = "proto3";
|
|
|
|
package cosyvoice;
|
|
option go_package = "protos/";
|
|
|
|
service CosyVoice{
|
|
rpc Inference(Request) returns (stream Response) {}
|
|
}
|
|
|
|
message Request{
|
|
oneof RequestPayload {
|
|
sftRequest sft_request = 1;
|
|
zeroshotRequest zero_shot_request = 2;
|
|
crosslingualRequest cross_lingual_request = 3;
|
|
instructRequest instruct_request = 4;
|
|
}
|
|
}
|
|
|
|
message sftRequest{
|
|
string spk_id = 1;
|
|
string tts_text = 2;
|
|
}
|
|
|
|
message zeroshotRequest{
|
|
string tts_text = 1;
|
|
string prompt_text = 2;
|
|
bytes prompt_audio = 3;
|
|
}
|
|
|
|
message crosslingualRequest{
|
|
string tts_text = 1;
|
|
bytes prompt_audio = 2;
|
|
}
|
|
|
|
message instructRequest{
|
|
string tts_text = 1;
|
|
string spk_id = 2;
|
|
string instruct_text = 3;
|
|
}
|
|
|
|
message Response{
|
|
bytes tts_audio = 1;
|
|
} |