Features Pricing Blog Docs FAQ Download
Documentation Menu

Translation Guide

Convert speech from any supported language to English text output.

Key concept Translation mode converts speech in ANY supported source language into ENGLISH text output. This is different from transcription, which preserves the original language.

What is Translation Mode?

MurmurTone's translation feature uses Whisper's built-in translation capabilities to convert spoken audio from any of 17 supported languages directly into English text. This happens in real-time as you speak.

Unlike separate transcription and translation services, Whisper performs speech-to-English-text in a single step, which often produces more natural results than transcribing first and then translating.

Translation vs Transcription

Choose the right mode for your use case:

Transcription (Default)

Use when you want text in the same language you're speaking.

  • Speak Spanish, get Spanish text
  • Speak Japanese, get Japanese text
  • Preserves original language

Translation

Use when you want English text regardless of what language you speak.

  • Speak Spanish, get English text
  • Speak Japanese, get English text
  • Always outputs English

Common Use Cases for Translation

Supported Languages

MurmurTone can translate from any of these languages to English:

LanguageCodeNotes
Auto-detectautoRecommended - automatically detects your language
EnglishenUseful for heavy accents or non-native speakers
SpanishesAll Spanish variants supported
Frenchfr
Germande
Italianit
PortugueseptBrazilian and European Portuguese
Dutchnl
Russianru
ChinesezhMandarin; Simplified and Traditional
Japaneseja
Koreanko
ArabicarModern Standard Arabic
Hindihi
Polishpl
Turkishtr
Vietnamesevi
Thaith
Auto-detect recommended In most cases, leave the source language set to "Auto-detect". Whisper is very accurate at identifying the spoken language. Only set a specific language if you're experiencing detection issues.

Model Recommendations

Translation quality varies significantly by model size. Larger models produce more accurate and natural-sounding translations.

ModelTranslation QualityBest For
Quick (tiny)BasicSimple phrases only; may miss nuances
Standard (base)GoodCasual use; simple sentences
Recommended (small)Very GoodMost users; good balance of speed and quality
Professional (medium)ExcellentComplex sentences; technical content
Studio (large-v3)BestMaximum accuracy; professional translation
For translation, bigger is better If translation quality is important to you, consider using the "Professional" or "Studio" model. The quality difference is more noticeable for translation than for same-language transcription.

How to Enable Translation

  1. Right-click the MurmurTone icon in your system tray
  2. Select Settings
  3. Go to the Recognition tab
  4. Scroll down to the Translation section
  5. Toggle Enable translation on
  6. Optionally set a specific source language (or leave on Auto-detect)
  7. Click Save

Once enabled, all your voice recordings will be translated to English instead of transcribed in the original language.

Troubleshooting

Wrong language detected

If auto-detection keeps picking the wrong language:

Poor translation quality

If translations seem inaccurate or unnatural:

Translation not working

If you're still getting text in your spoken language:

Mixed language output

If you're getting a mix of English and your source language: