Skip to content

param build fixes for audio models #208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
xiong-binbin merged 3 commits into from
Apr 27, 2026
Merged

param build fixes for audio models #208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
54d509b
fix(websocket): fix close code error used
songguocola Apr 23, 2026
a0eba15
feat(model/cosyvoice): add parameters support in body build
songguocola Apr 27, 2026
235b60f
feat(model/live-translate): fix params build
songguocola Apr 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions src/main/java/com/alibaba/dashscope/audio/http_tts/HttpSpeechSynthesisParam.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@

import com.alibaba.dashscope.base.HalfDuplexServiceParam;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.google.gson.JsonObject;
import java.nio.ByteBuffer;
import lombok.*;
Expand Down Expand Up @@ -80,6 +81,9 @@ public JsonObject getHttpBody() {
if (pitch != null) {
input.addProperty("pitch", pitch);
}
if (parameters != null && !parameters.isEmpty()) {
JsonUtils.merge(input, JsonUtils.parametersToJsonObject(parameters));
}

body.add("input", input);

Expand Down
16 changes: 12 additions & 4 deletions src/main/java/com/alibaba/dashscope/audio/omni/OmniRealtimeConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,9 @@ public class OmniRealtimeConfig {
public JsonObject getConfig() {
Map<String, Object> config = new HashMap<>();
config.put(OmniRealtimeConstants.MODALITIES, modalities);
config.put(OmniRealtimeConstants.VOICE, voice);
if (voice != null) {
config.put(OmniRealtimeConstants.VOICE, voice);
}
config.put(OmniRealtimeConstants.INPUT_AUDIO_FORMAT, inputAudioFormat);
config.put(OmniRealtimeConstants.OUTPUT_AUDIO_FORMAT, outputAudioFormat);
if (enableInputAudioTranscription) {
Expand Down Expand Up @@ -95,8 +97,6 @@ public JsonObject getConfig() {
OmniRealtimeConstants.TRANSLATION_CORPUS, this.translationConfig.getCorpus());
}
config.put(OmniRealtimeConstants.TRANSLATION, translationConfig);
} else {
config.put(OmniRealtimeConstants.TRANSLATION, null);
}
// Add transcription configuration for qwen-asr-realtime
if (transcriptionConfig != null) {
Expand All @@ -119,7 +119,15 @@ public JsonObject getConfig() {
OmniRealtimeConstants.INPUT_AUDIO_TRANSCRIPTION_CORPUS,
this.transcriptionConfig.getCorpus());
}
config.put(OmniRealtimeConstants.INPUT_AUDIO_TRANSCRIPTION, transcriptionConfig);
Object existingConfig = config.get(OmniRealtimeConstants.INPUT_AUDIO_TRANSCRIPTION);
if (existingConfig instanceof Map) {
@SuppressWarnings("unchecked")
Map<String, Object> tempMap = (Map<String, Object>) existingConfig;
tempMap.putAll(transcriptionConfig);
config.put(OmniRealtimeConstants.INPUT_AUDIO_TRANSCRIPTION, tempMap);
} else {
config.put(OmniRealtimeConstants.INPUT_AUDIO_TRANSCRIPTION, transcriptionConfig);
}
Comment thread
songguocola marked this conversation as resolved.
}
if (parameters != null) {
for (Map.Entry<String, Object> entry : parameters.entrySet()) {
Expand Down
8 changes: 4 additions & 4 deletions src/main/java/com/alibaba/dashscope/protocol/okhttp/OkHttpWebSocketClient.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,7 @@ public void onFailure(WebSocket webSocket, Throwable t, Response response) {

if (isClosed.get()) {
log.debug("called close before but not working, close again in onFailure.");
close(1013, "call closed before");
close(1001, "call closed before");
Comment thread
songguocola marked this conversation as resolved.
return;
}

Expand Down Expand Up @@ -240,7 +240,7 @@ public void onFailure(WebSocket webSocket, Throwable t, Response response) {
public void onMessage(WebSocket webSocket, String text) {
if (isClosed.get()) {
log.debug("called close before but not working, close again in onMessage.");
close(1013, "call closed before");
close(1001, "call closed before");
return;
}
log.debug(text);
Expand Down Expand Up @@ -339,7 +339,7 @@ public void onMessage(WebSocket webSocket, ByteString bytes) {
// Invoked when a binary (type 0x2) message has been received.
if (isClosed.get()) {
log.debug("called close before but not working, close again in onMessage.");
close(1013, "call closed before");
close(1001, "call closed before");
return;
}
if (!isFirstMessage.get()) {
Expand All @@ -363,7 +363,7 @@ public void onOpen(WebSocket webSocket, Response response) {
// messages..
if (isClosed.get()) {
log.debug("called close before but not working, close again in onOpen.");
close(1013, "call closed before");
close(1001, "call closed before");
return;
}
isOpen.set(true);
Expand Down
Loading