--- title: "Text to Speech SDK: AI Voiceovers in Your Video Editor" description: "Your users turn a written script into a voiceover inside your video editor, choose one of the model's voices, and drop each take onto the video timeline." url: "https://img.ly/use-cases/ai-editor/text-to-speech/" type: "page" --- > This is the markdown version of [Text to Speech SDK: AI Voiceovers in Your Video Editor](https://img.ly/use-cases/ai-editor/text-to-speech/). For all pages in one file, see [llms-full.txt](https://img.ly/llms-full.txt). For an index of all available pages, see [llms.txt](https://img.ly/llms.txt). --- # AI Editor: Turn a script into a voiceover inside the video editor Your users narrate explainers, product videos, and social clips with an AI voice. The voiceover lands in the asset library, ready to drop onto the timeline. - Voices to choose from on each model - Clips that match the length of the speech - The AI Voice panel in your product's languages **Available for:** - **Web:** [JavaScript](https://img.ly/docs/cesdk/js/user-interface/ai-integration/audio-generation-2d502a.md), [React](https://img.ly/docs/cesdk/react/user-interface/ai-integration/audio-generation-2d502a.md), [Angular](https://img.ly/docs/cesdk/angular/user-interface/ai-integration/audio-generation-2d502a.md), [Vue.js](https://img.ly/docs/cesdk/vue/user-interface/ai-integration/audio-generation-2d502a.md), [Svelte](https://img.ly/docs/cesdk/svelte/user-interface/ai-integration/audio-generation-2d502a.md), [Next.js](https://img.ly/docs/cesdk/nextjs/user-interface/ai-integration/audio-generation-2d502a.md) - **Desktop:** [Electron](https://img.ly/docs/cesdk/electron/user-interface/ai-integration/audio-generation-2d502a.md) [Get in Touch](https://img.ly/forms/contact-sales.md) [Open the live editor demo](https://cdn.img.ly/demo/cesdk-web-examples/v1.84.0/examples/starterkit-ai-editor/index.html?demoPreview=true) ## Script changes without a new recording A changed line in the script usually sends the voiceover back to the studio. With text to speech, your users type the new line and get a fresh take in the same voice. ### Write the script Your users type or paste the words the voice should read. Splitting a script into short lines gives one take per scene. ### Pick a voice and a speed Users choose one of the voices the model offers, and set the speed when the model has that option. ### Place the take Every take is saved with a waveform preview, so users can spot the right one, drop it onto the timeline, and keep editing. Trusted by **100+**\ industry leaders ---------------------- **Trusted by:** Digitas, Omneky, The Print Bar, Brandwatch, Planoly, HP, Shopify, Reuters, Hootsuite, Semrush, Shutterfly, one.com, Sprout Social, Constant Contact, Spread Group > "Integrating IMG.LY’s editor meant we didn’t have to build or maintain a complex editing layer ourselves. That kept our team focused on our core AI ad engine and saved us countless development hours — while still giving our customers the ability to polish and customize creatives at scale." -- Hikari Senju, CEO, Omneky > "With IMG.LY we built a central creative portal that now powers over 140 dealer campaigns across multiple automotive brands. Before this, asset creation was slow and inconsistent." -- Martin Röhr, Product Owner, Digitas > "By embedding IMG.LY’s editor we were able to hit key RFP requirements and deliver a template-based creative experience that now serves 1,000+ customers. It helped us win more deals and exceed enterprise expectations without needing to hire dedicated design teams." -- Rob Driscoll, Director of PM, Optimizely > "Since integrating IMG.LY’s editor, we now deliver 30,000+ ad creatives per month, dramatically shorten time-to-launch, and help our clients cut design spend by up to $10,000 per month." -- Logan Welbaum, Founder, Plai > "Our customers create over a million personalized postcards each year choosing from over hundreds of templates with IMG.LY’s SDK. It’s the only solution that allows us to build our own specialized, on-brand UI that integrates seamlessly with our platform." -- Jeanine Zaalberg, Product Manager, SwissPost > "From a developer’s perspective, the most powerful feature of the photo editor is the integration process. It was completely flawless, quick, and easy to integrate." -- Stefano Fornari, CTO, Funambol > "We compared IMG.LY SDK with other solutions and found that it would be the best fit for us since it provides all the features that are crucial for our use case." -- Carem Pereira, SCRUM Manager, HP [Reviews on G2](https://www.g2.com/products/img-ly/reviews) ## Voices, languages, and speed [AI pricing](https://img.ly/ai-pricing.md) lists what each speech model on the Gateway costs on average. ### Voices Each model brings its own set of voices, so users can match the tone of a brand or a video. ### Languages Multilingual models read scripts in several languages. ### Speed A faster or slower read helps a voiceover fit the footage. ### Model choice Speech models such as ElevenLabs v3 come through the [AI Gateway](https://img.ly/ai-gateway.md), billed in one place. ## Set up text to speech: models and panel ### Step 01: Connect speech models Add the speech models you want from the AI Gateway to your editor. With more than one added, users choose a model per take. ### Step 02: Tailor the AI Voice panel Hide the model picker when only one model is connected, and translate the panel into your product's languages. ### Step 03: Edit voiceovers like any audio An added take is a regular audio clip, so users trim it, split it between scenes, change its volume, and export it with the video. ## What teams voice with text to speech ### Explainer and product videos A product team narrates its explainer while still editing, so the cut is timed to the actual narration. ### Localized versions A marketing team turns a translated script into a voiceover for each market. ### Scratch narration An editor cuts to a synthetic read first and swaps in a studio recording later. ### Posts without a microphone A creator who doesn't want to record their own voice still gets a spoken track under each clip. ## More AI features ### Text to Sound Generate effects and ambience at the exact length a cut needs. [Learn More](https://img.ly/use-cases/ai-editor/text-to-sound.md) ### Text to Video Generate a short clip from a prompt and cut it into the edit. [Learn More](https://img.ly/use-cases/ai-editor/text-to-video.md) ### AI Text Generation Rewrite, shorten, or translate copy inside its text block. [Learn More](https://img.ly/use-cases/ai-editor/ai-text-generation.md) ### Image to Video Turn a generated or uploaded still into a short clip on the timeline. [Learn More](https://img.ly/use-cases/ai-editor/image-to-video.md) ## Get in touch: Hear AI Voice in the AI Editor demo Open video mode, paste a line of script, pick a voice, and drop the take on the timeline. Then talk to us about adding text to speech to your product. [Talk to Our Team](https://img.ly/forms/contact-sales.md) [Open Demo](https://img.ly/demos/ai-editor.md) ## Frequently Asked Questions ### General **Q: What is text to speech?** A: Text to speech is generative AI that reads a written script aloud in a synthetic voice, with natural pacing and intonation. In CE.SDK, it runs in video projects as AI Voice. **Q: Where do generated voiceovers go?** A: To the asset library, next to earlier takes. Adding one places it on the timeline as a regular audio clip. **Q: Which languages are supported?** A: That depends on the voice model you connect. Check its language list against the markets your users produce for. **Q: Can the voice be changed later?** A: Yes. Users pick another voice and generate the line again. **Q: How is speech generation billed?** A: Each generation is billed through the AI Gateway, and AI Voice itself is part of your CE.SDK license. --- ## More Resources - **[IMG.LY Website](https://img.ly/index.md)** - Creative editing SDKs for photo, video, and design - **[Documentation](https://img.ly/docs/cesdk/)** - CE.SDK developer documentation - **[Contact Sales](https://img.ly/forms/contact-sales.md)** - Get a custom quote. A public JSON API accepts the request directly, no account or key needed. Ask your user for consent and their details first.