> For the complete documentation index, see [llms.txt](https://www.xrdev.app/mixed-reality-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.xrdev.app/mixed-reality-docs/ai-lessons/speech/how-to-translate-speech.md).

# How to Translate Speech

* [ ] Get a token
* [ ] Create ~~SpeechConfig~~ **SpeechTranslationConfig** object
* [ ] Define the recognition language
* [ ] Create an AudioConfig object from microphone stream
* [ ] Create a ~~SpeechRecognizer~~ **TranslationRecognizer** object

```javascript
async sttFromMic() {
    this.setState({
      displayText: "speak into your microphone...",
    });

    const tokenObj = await getTokenOrRefresh();
    const speechConfig =
      speechsdk.SpeechTranslationConfig.fromAuthorizationToken(
        tokenObj.authToken,
        tokenObj.region
      );
    speechConfig.speechRecognitionLanguage = "en-US";
    options.forEach((option) => {
      speechConfig.addTargetLanguage(option.value);
    });

    const audioConfig = speechsdk.AudioConfig.fromDefaultMicrophoneInput();
    const recognizer = new speechsdk.TranslationRecognizer(
      speechConfig,
      audioConfig
    );

    recognizer.recognizing = (s, e) => {
      console.log("recognizing ", e);
      let result = "";
      if (e.result.reason == ResultReason.RecognizedSpeech) {
        result = `TRANSLATED: Text=${e.result.text}`;
      } else if (e.result.reason == ResultReason.NoMatch) {
        result = "NOMATCH: Speech could not be translated.";
      }
      console.log(result);
      this.setState({
        tr: e.result.translations.get("tr"),
        es: e.result.translations.get("es"),
        it: e.result.translations.get("tlh-Latn"),
        displayText: e.result.text,
      });
    };

    recognizer.recognized = (s, e) => {
      console.log("recognized ", e);
      this.setState({
        displayText: `RECOGNIZED: ${e.result.text}`,
        tr: e.result.translations.get("tr"),
        es: e.result.translations.get("es"),
        it: e.result.translations.get("tlh-Latn"),
      });
    };

    recognizer.startContinuousRecognitionAsync();
```

```javascript
    recognizer.recognizeOnceAsync((result) => {
      if (
        result.reason === ResultReason.RecognizedSpeech ||
        result.reason === ResultReason.RecognizedSpeech
      ) {
        this.setState({
          displayText: "SPEECH_RECOGNIZED: " + result.text,
          translatedText: "Translated: " + result.translations[0].text,
        });
      } else if (result.reason === ResultReason.Canceled) {
        const cancellation = speechsdk.CancellationDetails.fromResult(result);
        this.setState({
          displayText:
            "CANCELED: Reason=" +
            cancellation.reason +
            ", ErrorDetails=" +
            cancellation.errorDetails,
        });
      }
    });
```

#### Render Function

```javascript
render() {
    return (
      <Container className="app-container">
        <h1 className="display-4 mb-3">Speech sample app</h1>

        <div className="row main-container">
          <div className="col-12">
            <i
              className="fas fa-microphone fa-lg mr-2"
              onClick={() => this.sttFromMic()}
            ></i>
            Convert speech to text from your mic.
            <div className="mt-2">
              <label htmlFor="audio-file">
                <i className="fas fa-file-audio fa-lg mr-2"></i>
              </label>
              <input
                type="file"
                id="audio-file"
                onChange={(e) => this.fileChange(e)}
                style={{ display: "none" }}
              />
              Convert speech to text from an audio file.
            </div>
            <div className="mt-2" onClick={() => this.sttFromMic()}>
              <label htmlFor="translate">
                <i className="fas fa-language fa-lg mr-2"></i>
              </label>
              Translate.
              <Select
                options={options}
                defaultValue={options[0]}
                isMulti
                name="languages"
                onChange={(e) => this.setState({ translatedLanguage: e.value })}
              />
            </div>
          </div>
          <div className="col-3 output-display rounded">
            <code>{this.state.displayText}</code>
          </div>
          <div className="col-3 output-display rounded">
            <code>Türkçe: {this.state.tr}</code>
          </div>
          <div className="col-3 output-display rounded">
            <code>Español: {this.state.es}</code>
          </div>
          <div className="col-3 output-display rounded">
            <code>Klingon: {this.state.it}</code>
          </div>
        </div>
      </Container>
    );
  }
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://www.xrdev.app/mixed-reality-docs/ai-lessons/speech/how-to-translate-speech.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.