draft : text to speed , offline code.in java(key) instead of pyton, reason why pyton (not asking subkey), where java asks?
//not testing, for java it is asking subscription key.
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.HttpResponse;
import org.apache.http.util.EntityUtils;
import org.json.JSONObject;
import javax.sound.sampled.*;
import java.io.*;
import java.nio.file.*;
import java.util.ArrayList;
import java.util.List;
public class TextToSpeechEdgeTTS {
static final String INPUT_FILE = "input.txt";
static final String VOICE = "te-IN-ShrutiNeural";
static final int CHUNK_SIZE = 4000;
static final String TEMP_DIR = "temp_chunks";
static final String FINAL_MP3 = "output.mp3";
public static void main(String[] args) throws Exception {
String text = readText(INPUT_FILE);
if (text.isEmpty()) return;
List<String> chunks = chunkText(text, CHUNK_SIZE);
new File(TEMP_DIR).mkdirs();
List<File> chunkFiles = new ArrayList<>();
int idx = 0;
for (String chunk : chunks) {
String rate = mapSpeedToRate(5); // set desired speed 1–7
File chunkFile = new File(TEMP_DIR + "/chunk_" + idx + ".mp3");
generateChunk(chunk, chunkFile, VOICE, rate);
chunkFiles.add(chunkFile);
System.out.println("Generated chunk: " + chunkFile.getName());
idx++;
}
mergeAudioFiles(chunkFiles, FINAL_MP3);
System.out.println("✅ Final audio saved to: " + FINAL_MP3);
cleanup();
}
static String readText(String path) throws IOException {
return new String(Files.readAllBytes(Paths.get(path))).replaceAll("\\s+", " ");
}
static List<String> chunkText(String text, int maxLength) {
List<String> chunks = new ArrayList<>();
while (!text.isEmpty()) {
if (text.length() <= maxLength) {
chunks.add(text);
break;
}
int splitAt = text.lastIndexOf(' ', maxLength);
if (splitAt == -1) splitAt = maxLength;
chunks.add(text.substring(0, splitAt));
text = text.substring(splitAt).trim();
}
return chunks;
}
static String mapSpeedToRate(int value) {
return switch (value) {
case 1 -> "-75%";
case 2 -> "-50%";
case 3 -> "0%";
case 4 -> "+25%";
case 5 -> "+50%";
case 6 -> "+75%";
case 7 -> "+100%";
default -> "0%";
};
}
static void generateChunk(String text, File outputFile, String voice, String rate) throws Exception {
String ssml = "<speak version='1.0' xml:lang='te-IN'>" +
"<prosody rate='" + rate + "'>" + escapeXml(text) + "</prosody></speak>";
String tokenUrl = "https://eastus.tts.speech.microsoft.com/cognitiveservices/v1";
HttpPost post = new HttpPost(tokenUrl);
post.setHeader("Content-Type", "application/ssml+xml");
post.setHeader("X-Microsoft-OutputFormat", "audio-16khz-128kbitrate-mono-mp3");
post.setHeader("User-Agent", "JavaEdgeTTS");
post.setHeader("Ocp-Apim-Subscription-Key", "YOUR_SUBSCRIPTION_KEY"); // 🔑 Replace with valid Azure key
post.setEntity(new StringEntity(ssml));
try (CloseableHttpClient client = HttpClients.createDefault()) {
HttpResponse response = client.execute(post);
byte[] audioBytes = EntityUtils.toByteArray(response.getEntity());
Files.write(outputFile.toPath(), audioBytes);
}
}
static String escapeXml(String s) {
return s.replace("&", "&").replace("<", "<")
.replace(">", ">").replace("\"", """).replace("'", "'");
}
static void mergeAudioFiles(List<File> inputFiles, String outputFile) throws IOException {
try (FileOutputStream fos = new FileOutputStream(outputFile)) {
for (File file : inputFiles) {
Files.copy(file.toPath(), fos);
}
}
}
static void cleanup() throws IOException {
for (File file : new File(TEMP_DIR).listFiles()) {
file.delete();
}
new File(TEMP_DIR).delete();
System.out.println("🧹 Temp files cleaned up.");
}
}
🔑 Important Note:
To make the above code work:
You must have a valid Microsoft Azure TTS Subscription Key
You can get it from: https://portal.azure.com > Create a Cognitive Services > Speech
Replace this line with your actual key:
java
Copy
Edit
post.setHeader("Ocp-Apim-Subscription-Key", "YOUR_SUBSCRIPTION_KEY");
Would you like a downloadable ZIP with:
All required .jar files
A working Eclipse project with this code?
Or do you prefer converting this into a Maven-based project for better dependency management?
You said:
httpclient-4.5.13.jar, httpcore-4.4.13.jar download links for these two
ChatGPT said:
You're giving feedback on a new version of ChatGPT.
Which response do you prefer? Responses may take a moment to load.
ChatGPT
Response 1
Here are the official Maven Central download links for the JAR files:
✅ Apache HttpClient 4.5.13
JAR Download:
httpclient-4.5.13.jar
✅ Apache HttpCore 4.4.13
JAR Download:
httpcore-4.4.13.jar
⚠️ Note:
httpclient depends on httpcore, so both are required.
----------
Why Python code using edge-tts doesn't need a subscription key, but Java does:
🔹 Python Code Uses edge-tts (Unofficial Microsoft Edge TTS API Wrapper)
-
The Python
edge-ttslibrary uses undocumented internal endpoints used by the Microsoft Edge browser. -
It mimics browser behavior and sends requests to Edge's public endpoints that do not require authentication or an API key.
-
This works because Microsoft exposes some TTS capabilities directly for Edge users — it’s free, fast, and doesn’t require any API token.
🔒 But: This is unofficial and may stop working if Microsoft changes their internal APIs.
🔹 Java Code Uses Microsoft Azure Cognitive Services
-
The Java approach uses the official Microsoft Azure Speech Service.
-
This service is secure and enterprise-grade, and thus requires:
-
Subscription key
-
Region endpoint
-
-
Authentication ensures Microsoft tracks usage, enforces quotas, and prevents abuse.
📊 Summary:
| Feature | Python (edge-tts) | Java (Azure SDK) |
|---|---|---|
| Uses official API | ❌ No | ✅ Yes |
| Requires subscription key | ❌ No | ✅ Yes |
| Free quota/limit control | ❌ None guaranteed | ✅ With Azure portal settings |
| Reliability | ⚠️ May break anytime | ✅ Stable, backed by Azure |
Would you prefer switching to Python for ease or want help registering a free Azure TTS subscription key for Java use?
You said:
ChatGPT said:
That’s a significant jump, both in salary and in work flexibility. Let’s break it down so you can assess it clearly.
📊 Current vs. New Offer Overview
| Category | IBM (Current) | NBCU (Offer) |
|---|---|---|
| CTC | ₹24 LPA | ₹38 LPA (Fixed) |
| Work Mode | Remote (unofficially managed) | Official Remote |
| Joining Notice | - | 45 days (requested) |
| Employer | IBM | NBCUniversal (NBCU) |
✅ Pros of NBCU Offer
-
~58% hike in fixed pay — very strong.
-
Official remote: removes the stress of hiding or bending rules.
-
Likely better international exposure, given NBCU's global presence.
-
Could improve work-life balance, assuming team culture supports it.
⚠️ Things to Consider
-
Joining Timeline: If IBM enforces a 90-day notice, will NBCU flex the 45-day requirement?
-
Buyout Option: Can NBCU buy out your remaining notice if IBM won't relieve early?
-
Team Fit: Is the NBCU team technically strong, collaborative, and aligned with your goals?
-
Contract/Employment Type: Confirm it's permanent (not via a vendor or third-party).
💬 Suggested Next Steps
-
Negotiate notice period with NBCU — share IBM’s policy and see if they can accept a 60-day join or help with buyout.
-
Ask for offer letter and ensure:
-
Fixed vs. variable clearly mentioned.
-
Remote clause mentioned.
-
Onboarding process and team structure are clear.
-
-
If comfortable, resign from IBM only after NBCU documentation is firm.
Also make sure you include commons-logging-1.2.jar if not already added.
Would you like me to prepare a .zip file with all 3 JARs bundled for Eclipse or a Maven project setup?
