NEW! ElevenLabs Voiceover Studio!

Bob Doyle Media
11 May 202418:05

TLDR11 Labs has introduced a new feature called Voiceover Studio, which allows users to add multiple characters and voiceovers to existing videos using any voice from their 11 Labs library. The tool also supports the addition of multiple layers of sound effects and has a built-in video editor for easy manipulation of the video's timeline. A demonstration was conducted using a service called bu to create a short video about a zoo visit, which was then edited in Voiceover Studio with character dialogues and sound effects. The process showcased the ability to adjust the pace, volume, and even regenerate audio with dynamic duration for a more natural flow. The tool's potential for creativity was highlighted, with the suggestion that future updates, including music generation, could further enhance the user experience.

Takeaways

  • 🎉 ElevenLabs has announced its entry into AI music generation, competing with other platforms like Soono and Udio.
  • 🎧 Demos of ElevenLabs' music generation are available online and are reportedly of high quality.
  • 📢 The author has requested access to ElevenLabs' music generation and will share it once available.
  • 🎥 Introduction of a new feature by ElevenLabs called Voiceover Studio, which allows users to add multiple characters and sound effects to existing videos.
  • 📚 The Voiceover Studio feature includes a video editor for creating and editing voiceovers and sound effects.
  • 🦜 The process of creating a video involves generating a script, subtitles, voiceovers, and the final video.
  • 🧩 Users can customize the video by changing images, voices, and music within the Voiceover Studio.
  • ✂️ The video can be edited on a timeline, allowing for the removal of unwanted content.
  • 🔊 Sound effects can be added and adjusted in volume to complement the voiceover.
  • 🎭 Users can create dialogues with different characters and adjust the pacing and style of the voiceovers.
  • 🌐 The tool supports generating voiceovers in different languages, with the ability to add new languages and regenerate audio.
  • 📈 The author suggests that with planning, users can create compelling content using the Voiceover Studio.

Q & A

  • What is the big news from 11 Labs in the field of Creative AI?

    -11 Labs has announced their entry into the AI music generation space, competing against other platforms like Soono and Udio. Their demos are reportedly of high quality, setting them apart from their competitors.

  • What is the new feature introduced by 11 Labs called?

    -The new feature is called Voiceover Studio, which allows users to add multiple characters and voices to existing videos, along with multiple layers of sound effects.

  • How does the Voiceover Studio enable video editing?

    -Voiceover Studio includes a video editor within 11 Labs that allows users to create and edit videos, change images, voices, and music, and layer sound effects.

  • What service is used to create a random video for the demonstration?

    -The service used to create a random video for the demonstration is called 'bu'.

  • How long does it take to generate a video using the service 'bu'?

    -It takes about 45 seconds to create a video using the service 'bu'.

  • What can you do with the video once it's created in 11 Labs?

    -Once the video is created in 11 Labs, you can add voiceover tracks, sound effects, and edit the timeline. You can also export the video and add target languages for multilingual support.

  • How does the Voiceover Studio handle multiple voice characters?

    -The Voiceover Studio allows users to select from their existing voice library or create new voices for characters. It supports adding dialogue for two or more characters and layering them on separate tracks.

  • What kind of sound effects can be added to a video using Voiceover Studio?

    -Voiceover Studio enables the addition of various sound effects, which can be generated through text prompts, such as outdoor nature sounds, birds chirping, crickets, or even specific animal sounds like a bear growling.

  • How does the user adjust the speed and pacing of the voiceovers?

    -The user can adjust the speed and pacing of the voiceovers by regenerating the audio with dynamic duration, which allows for a more naturally paced speech.

  • What is the process for changing the language of the voiceover?

    -To change the language of the voiceover, the user can click on the 'plus sign' to choose a target language, which creates duplicate tracks and mutes the previous tracks. Then, the user regenerates all of the spoken tracks in the selected language.

  • How does the Voiceover Studio help in managing different audio tracks?

    -The Voiceover Studio provides a timeline interface where users can manage different audio tracks, adjust their order, trim or extend them, and control the volume levels independently.

Outlines

00:00

🎵 AI Music Generation and Voiceover Studio Introduction

The first paragraph introduces the audience to 11 Labs' entry into the AI music generation market, positioning it against competitors like Soono and Auido. The narrator mentions high-quality demos available online and expresses excitement about the potential access to these tools. The focus then shifts to a new feature by 11 Labs called Voiceover Studio, which allows users to add multiple characters and sound effects to existing videos. The narrator guides the audience through creating a video using a service called 'bu' and then importing it into 11 Labs to add voiceovers and sound effects, demonstrating the process with a fictional story about Bob and Tracy visiting a zoo.

05:02

🎧 Customizing Voiceover and Sound Effects

The second paragraph delves into the customization options available in the Voiceover Studio. The narrator discusses how to adjust the pacing of the voiceover by regenerating audio with dynamic duration, and how to layer multiple sound effects tracks to enhance the video. It also covers the process of adding and adjusting the volume of sound effects, such as outdoor nature sounds, birds chirping, and even a bear growling, to complement the dialogue between the characters Bob, Tracy, and a third character, Adam. The paragraph showcases the versatility of the tool in creating a humorous and dynamic audio experience for the video.

10:05

🦈 Adding Character Voices and Interactive Dialogue

In the third paragraph, the focus is on incorporating character voices and interactive dialogue into the video. The narrator describes how to add new characters, such as Adam, and create a more engaging and humorous dialogue between the characters. It also touches on the process of adding sound effects like dolphin chatter to enhance the narrative. The paragraph highlights the ability to adjust the volume and timing of voiceovers and sound effects to create a coherent and entertaining audiovisual experience, emphasizing the creative possibilities offered by the Voiceover Studio.

15:07

🌐 Language Translation and Final Touches

The fourth paragraph covers the language translation feature of the Voiceover Studio. The narrator demonstrates how to add a new language, in this case, French, to the existing voiceover tracks. It discusses the process of regenerating audio in the new language, adjusting the pacing for natural speech, and aligning the translated tracks with the original audio. The paragraph concludes with the narrator exporting the video in both English and French, showcasing the tool's capability to create multilingual content. The narrator also teases the potential for future features, such as music generation, and encourages viewers to explore the tool further.

Mindmap

Keywords

💡Creative AI

Creative AI refers to the use of artificial intelligence in the field of creative tasks such as music, art, and writing. In the context of the video, 11 Labs is entering the AI music generation space, which is a subset of Creative AI, indicating their involvement in using AI for creating music.

💡Voiceover Studio

Voiceover Studio is a feature within 11 Labs that allows users to add multiple character voices and sound effects to existing videos. It is showcased in the video as a new tool that enables video editing with the integration of various voiceovers and sound effects to enhance the storytelling of a video.

💡AI Music Generation

AI Music Generation is the process of using artificial intelligence to create music. The video discusses 11 Labs' entry into this space, suggesting that their technology is capable of producing high-quality music that is competitive with other existing platforms.

💡Sound Effects

Sound Effects are artificially created sounds that are added to video or audio content to enhance the mood, atmosphere, or to provide additional information. In the script, the Voiceover Studio allows for the layering of multiple sound effects, such as 'birds chirping' or 'bear growling', to accompany the dialogue and create a more immersive experience.

💡Video Editor

A Video Editor is a software tool used for editing video footage, adding effects, and compiling final cuts. The video mentions a 'video editor inside 11', which implies that 11 Labs has integrated video editing capabilities within their platform, allowing users to edit and refine their videos with voiceovers and sound effects.

💡Script

A Script in the context of video production is a written text that serves as the dialogue or narrative for a video. The script is crucial for voiceover work, and the video demonstrates how the Voiceover Studio enables users to generate audio from text scripts and adjust the timing and pacing of the dialogue.

💡Dynamic Duration

Dynamic Duration is a feature that allows the pacing of the audio to adjust automatically based on the content of the script. This feature ensures that the speech sounds natural and is not rushed or too slow. In the video, it is used to improve the timing of the French translation of the dialogue.

💡Stability and Style

Stability and Style are parameters in the Voiceover Studio that affect the characteristics of the generated voiceover. Stability refers to how closely the voice adheres to a consistent tone and pace, while Style can influence the expressiveness or emotion conveyed by the voice. The video demonstrates how adjusting these parameters can change the feel of the voiceover.

💡Multi-track

Multi-track refers to the ability to work with multiple layers or tracks of audio in a project. This allows for complex audio production where different elements, such as dialogue, sound effects, and music, can be independently adjusted and mixed. The video script describes how the Voiceover Studio supports multi-track editing for detailed audio production.

💡Export

Export in video editing is the process of finalizing and saving the edited video in a specific format for sharing or distribution. The video script mentions exporting the video, indicating the completion of the editing process and preparation for the video to be shared or published.

💡Target Languages

Target Languages are the languages into which the original content, such as a video or audio, is translated or dubbed. The video script discusses adding a French version of the voiceover, which involves generating all spoken tracks in French, demonstrating the capability of the Voiceover Studio to support multiple languages.

Highlights

11 Labs announced entering the AI music generation space, competing with soono and udio.

Demos of 11 Labs' music generation are available online, showcasing high quality.

11 Labs' Voiceover Studio feature allows adding multiple characters and voices to existing videos.

Users can layer multiple sound effects within the Voiceover Studio.

The tool includes a video editor for creating and editing voiceover content.

A service called bu is used to create a base video for the voiceover demonstration.

The video creation process includes generating a script, subtitles, and voiceovers.

Editing in the timeline allows for the removal of unwanted content from the video.

11 Labs enables the creation of dialogue and voiceover tracks for different speakers.

The pacing of voiceovers can be adjusted for natural speech.

Sound effects can be generated and layered in the background of the voiceover.

Users can adjust the volume of individual sound effect clips.

The tool allows for the translation of voiceover content into different languages.

Dynamic duration can be used to adjust the pacing of translated voiceovers.

The Voiceover Studio provides basic audio editing features but lacks advanced options like EQ and reverb.

The process of adding and editing voiceovers is demonstrated with a humorous and fictional zoo visit story.

The final video can be exported with the edited voiceover and sound effects in the selected language.

11 Labs' Voiceover Studio is a new feature that offers creative possibilities for video content.