About AI voices

AI voices are created by training machine learning algorithms on the recorded voices of professional voice actors. Hence, they can transform the text into human-sounding voice-overs using speech synthesis.

Murf Studio presently supports voices in 20 languages, segmented into accents and age categories, for a total of 120+ different voice selections.


The different languages Murf supports are English | French | German | Italian | Spanish | Russian | Portuguese | Danish | Dutch | Arabic | Hindi | Tamil | Chinese | Japanese | Korean | Finnish | Norwegian | Romanian | Turkish | Indonesian

Voices and Plans

Murf's text-to-speech voices are split into two categories: Basic and Pro. 


  • These voices can be accessed with the Basic plan (monthly/annual), Pro plan & Enterprise plan (monthly/annual).
  • The basic voices consist of only 60 voice actors across ten languages.

The ten languages are as follows:

  1. English
  2. French
  3. German
  4. Italian
  5. Spanish
  6. Portuguese
  7. Russian
  8. Hindi
  9. Arabic
  10. Tamil


  • These voices can be accessed with the Pro plan (monthly/annual) and the Enterprise plan (monthly/annual) only.
  • Pro and Enterprise users can access both Basic and Pro voices.
  • The Pro voices consist of all 120+ voices across 20 languages available on Murf Studio.

Voice Customisation


The Pronunciation tool allows users to alter the pronunciation of any word in the project. This can be utilized when a specific voice cannot accurately pronounce a word.

There are 2 ways to alter the pronunciation of a word:

Alternative spelling :

  • This method deals with breaking down the word and spelling out the syllables for more accurate pronunciation.
  •  E.g., The word "Present" can be pronounced as "present" or "pre-zent" both having different meanings and pronunciations.

IPA (International Phonetic Alphabet):

  • In phonology and linguistics, a phoneme is a unit of sound that can distinguish one word from another in a particular language. 
  • We suggest using third-party websites like Tophonetics, Dictionary, Wiktionary, Easypronunciation, and other websites on Google to acquire the right IPA for the pronunciations.
  •  Eg: How: haʊ | Help: hˈɛlp | Recoil: riˈkɔɪl | Specific: spəsˈɪfɪk

The Pronunciation feature can be accessed by double clicking on the word that requires correction in pronunciation.

Pronunciation menu

Smart suggestions

Smart suggestions present a range of IPAs and alternative spellings for the word. To hear a preview of these smart suggestions, click the play button.

Add custom pronunciation

The studio accepts custom IPA and alternative spellings. They can be added to the list of suggested pronunciations under the "custom (personal)" tab by clicking on the Add Pronunciation button and can be accessed anytime in the future.

Important points:

    • After entering the pronunciation, it can be previewed by clicking on the preview button. 
    • For IPA to be applied in the project, you must click on Save. 
      • Failed to generate: This would occur if the system does not recognize the IPA entered. In such cases, try an alternative IPA.
      • If the error persists, reach out to the support team via email (support@murf.ai) or live chat, and we will assist you with the appropriate solution.
    • After saving IPA, the sentences containing the word will need to be re-rendered.

Apply and Apply to Project

    • The Apply button applies the new pronunciation to the word present in that particular sub-block only.
    • The "Apply to Project" button applies the pronunciation to the same word present throughout the project.

Manage Pronunciations

  • Once a custom pronunciation has been saved, it can be accessed by selecting Manage Pronunciation at the bottom of the menu.
  • Custom pronunciations can also be shared with your teams from this tab. 
  • Previously saved custom pronunciations are sorted by language. 
  • You can look up a previously saved custom pronunciation using the search bar.
  • The updated word will be highlighted in pink once the pronunciation has been updated.


The pause feature is an essential tool for syncing voice-over videos and presentations. Adding pauses also aids in achieving a more realistic output. 

There are a total of 3 ways to add a pause in the script:

  1. Pre-defined pauses
  2. Punctuation
  3. Increased block size

1. Pre-defined Pauses

  • Extra Weak (250ms), Weak (0.5s), Medium (0.75s), Strong (1s), Extra Strong (1.25s), 
  • Or enter a custom Pause time between 0.1 to 5.0 seconds.

2. Punctuation marks:

Certain punctuation marks, such as full stops (.) and commas (,) add a natural pause to the script. 

3. Increasing voice block size:

Longer pauses can be added at the end of each voice block by selecting the block from the bottom timeline and increasing the size by dragging the slider present. 

Once the pauses are updated, click on the generate button (play button) to generate audio and listen to the updated AI voice.

How to use 'Pause' to add Introductory Music? How to start the voice-over from the 'x' timestamp?

  • The first block of the project is to be left blank, and start your script from the second block. Or add a new block to the beginning of the script. 
  • Then select the first block from the timeline, stretch it, and increase the size to 'x.'
  • Use the play button to build and preview the project. 


The ear perceives the relative highness or lowness of a tone during speech. The pitch of the voice determines this. Using this option, the pitch of your voiceover can be adjusted. (Either high or low pitch)


1. Select the text block and click on the Pitch feature.

  • Once the text block is selected, the Pitch feature will be available within the text block.
  • Click on the node and move it to the left and right to increase and decrease the pitch accordingly.
  • For a deeper effect, lower the pitch below 50%.
  • Similarly, increase the pitch above +50% for a sharp or cartoonish effect.
  • Click on the Generate audio button to update the changes made.
  • Once updated, click the generate button (play button) to generate audio and listen to the updated AI voice.
  • Click on "Reset" to reset the counter to 0%.


  • Select the text block.
  • Drag the node and move from left to right to increase and decrease the speed. Move the scale below -50% for a slower pace. Similarly, for a faster pace, move the scale above +50%.
  • Click on the Generate audio button to update the changes made.
  • Once updated, click the generate button (play button) to generate audio and listen to the updated AI voice.
  • Click on Reset to default to reset the speed setting back to normal.


The Emphasis feature assists users in adding stress to the given word, changing the intonation of the sentence, and emphasizing a particular word or set of words.

Example: "Hey, how can I help you?"  

Using the emphasis feature, we can make this sentence sound more like a question than a statement. This is done b adding emphasis nodes towards the end of the sentence.

Emphasis menu

Click on the message icon with a star in the text block to open the Emphasis window.

Adding nodes in the Emphasis graph

  • The Emphasis graph shows the emphasis values on the Y-axis and the sentence on the X-axis. 
  • Nodes can be placed by clicking anywhere in the window. 
  • Upto 5 nodes can be added within the graph. 
  • Depending on the Y-axis value the node is placed at, the output would vary accordingly. 
  • Placing nodes right after the word you wish to emphasize gives the best results. 
  • Adding a weak pause or comma before the word you wish to emphasize also improves the final output. 
  • We recommend not placing the node too high or too low, as this would cause the voiceover to sound poor or distorted.


Clicking on the Preview button would generate a preview of the voice with emphasized words.

Remove node

The node can be removed by selecting it and clicking the Remove Node button.


Click the Reset button to remove all the nodes in the emphasis graph.


Click the Apply button to save the changes made to your project from the emphasis menu.

The emphasis button is now golden.

The Emphasis icon will now be golden to indicate that the text in the text block has been emphasized.

Legacy Emphasis

  • We have recently updated the logic by which the emphasis feature works.
  • The legacy emphasis refers to the older logic.
  • To switch to an earlier version of the Emphasis feature, enable "Legacy Emphasis." 
  • The previous emphasis logic altered the volume and energy of the voice to emphasize the words, whereas the current emphasis graph alters the pitch.


At Murf, we understand that every language may have different dialects, and it is essential to convey them perfectly.

The following languages support multiple text to speech accents: English, French, Spanish, Portuguese and Chinese 

EnglishUS & Canada









Age Group

Murf Studio currently has voices across the following age groups:

Young Adult: A young adult's voice can be attributed to up-beat, energetic, or enthusiastic voice-overs. Eighty-eight of our AI voices support this version across 20 Languages. Out of these, 39 are male and 49 female voices.

Middle-Aged: Voices have slightly deeper tones. We have 54 middle-aged voices available across 20 languages. Out of these, 28 are male, and 26 are female voices.

Children: We have three children's voices available in English (Kids), out of which two are female and one male voice.

Voice Styles

Users can use this feature to produce a more realistic voice over based on the video's theme or target demographic. 

The following voices support tones:

    • English (UK)
      • Eliza- General and Newscast (Basic Voice)
    • English (US & Canada)
      • Ava- General, Chat, Customer Service, Narration-professional, newscast- casual, Newscast- formal, Cheerful, Sad, Empathetic, Angy, Exited, Friendly, Terrified, Shouting, Unfriendly, Whispering, Hopeful (Basic Voice)
      • Adam- General, Newscast, and Conversational (Basic Voice)
      • Nate- General, Newscast, Angy, Cheerful, Sad, Excited, Friendly, Terrified, Shouting, Unfriendly, Whispering, Hopeful (Basic Voice)
      • Cathy- General, Assistant, Chat, Customerservice, Newscast, Angy, Cheerful, Sad, Excited, Friendly, Terrified, Shouting, Unfriendly, Whispering, and Hopeful(Pro Voice)
      • Jessica- General Newscast and Conversational (Pro Voice)
      • Rachel- General, Angy, Cheerful, Sad, Excited, Friendly, Terrified, Shouting, Unfriendly, Whispering, and Hopeful (Pro Voice)
      • Ken- Conversational, and Promo (Pro Voice)
      • Samantha- Coversational, and Luxury (Pro Voice)
      • Julie- Coversational, and Cheerful (Pro Voice)
    • Chinese (Simplified)
      • Liu- General, Assistant, Chat, Customer Service, Newscast, Affectionate, Angry, Calm, Cheerful, Disgruntled, Fearful, Gentle, Lyrical, Sad, Serious, and Poetry Reading (Pro Voice)
      • Chao- General, Embarrassed, Calm, Fearful, Cheerful, Disgruntled, Serious, Sad, and Angry (Pro Voice)
      • Hong- General, Customer service, Narration-professional, and Newscast- casual (Pro Voice)
    • Japanese
      • Sakura- General, Chat, Customer Service and Cheerful (Pro Voice)
    • Portuguese (Brazil)
      • Marcia- General and Calm (Pro Voice)

Voices Menu

  • Head to the "Explore AI Voices" tab to access the voices menu.
  • Or clicking on the image of the voice actor present at a block level also opens the voice selection menu. 
  • Here users can search, preview, filter, and apply voices to your entire project. 

Voices can be filtered in the Voices menu by:

Language - Accent