This free tool lets you upload an audio file of a conversation and generates two separate MP3 files, one for each speaker. Each file maintains the original length by replacing the non-speaking parts with silence, and it also creates a downloadable SRT file for easy captioning.
Perfect for use with AI-generated avatars like those from HeyGen, Synthesia, D-ID, Rephrase.ai, and DeepBrain AI, this tool enhances your videos with realistic conversations and seamless lip-sync animations, ideal for interactive content creation. Perfect for working with Audio Overview files from NotebookLM.
If you need just the SRT file, visit our other free tool .
Free Registration Available: Save your API key during registration, and it will be automatically populated when you use this tool. This convenient feature streamlines your workflow, allowing you to focus on creating seamless, interactive content without the hassle of re-entering your key each time.
Register for FreeUpload Your Audio File
Key Features:
- Create SRT files effortlessly for seamless integration with AI video platforms like HeyGen, Synthesia, and more.
- Advanced speaker separation to accurately isolate voices in multi-speaker conversations.
- Perfect for transcribing podcasts and dialogues, including those made with NotebookLM.
- High-precision transcription powered by AssemblyAI's state-of-the-art algorithms.
Privacy Policy
Our Commitment to Your Privacy
- API Key Security: Your AssemblyAI API key is never saved on our servers.
- File Storage: Your SRT file will be stored for 24 hours and then permanently deleted.
- Data Usage: Your audio and SRT files are never used for any purpose other than providing the transcription service you request.
- Confidentiality: We respect your privacy and the confidentiality of your content.
By using this service, you agree to these privacy terms. If you have any questions or concerns, please contact us.