Transcribe English and Spanish audio on CPU with faster-whisper and a pinned multilingual small model. This Ubuntu 24.04 AMI returns text with segment and word timestamps through a private HTTPS API with per-instance TLS. Audio stays on the instance, with no model API account or GPU needed.
This AMI turns speech in WAV, FLAC or MP3 files into text with segment and word timestamps, using faster-whisper (an efficient implementation of OpenAI's Whisper model) on CPU. It is for teams that transcribe meetings, interviews or support calls and want the audio processed privately in their own AWS account, without a per-minute API.
What you get: faster-whisper with a bundled multilingual small model for English and Spanish, an HTTPS API on port 8443 with a TLS certificate and access files created on first boot, and the full faster-whisper Python SDK for longer files. The API accepts files of up to 10 MiB and five minutes, one request at a time on t3.medium. For longer recordings, the SDK transcribes files directly by filename, offline (a 5 minute 31 second recording was verified on t3.medium). Diarization, translation, live streaming and voice generation are not included.
Getting started: launch t3.medium with at least 24 GiB of encrypted gp3 storage and IMDSv2, keep inbound application ports closed and connect with Session Manager. Run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh, forward port 8443 and transcribe your first file. Back up your data before replacing an instance.
Known issues: the 17 October 2026 host scan reports High and Critical matches in the pinned Ubuntu kernel and one FFmpeg advisory (CVE-2026-107696) in a network protocol that the shipped build disables; the Python runtime scan reports none. Read https://docs.softwaresushi.com/whisper-cpu/operations/#maintenance before deployment.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, setup documentation and maintenance by Software Sushi. faster-whisper and the bundled model are published under the MIT license; media libraries keep their own license notices. Software Sushi is independent of the upstream project and does not claim upstream or AWS endorsement. EC2, EBS and data transfer are billed separately from software charges.
Highlights
Transcribe English and Spanish audio on CPU, with no GPU or model API account.
Text with segment and word timestamps from WAV, FLAC or MP3.
Private HTTPS API with per-instance TLS, plus the offline SDK for longer recordings.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
This listing uses one usage-based dimension: an hourly software charge billed per running hour on the t3.medium instance type. You pay only while the instance runs, so cost scales with how many hours you keep it active. There are no tiers, bundles, or annual commitment to choose from. Stopping or terminating the instance stops the hourly software charge. AWS infrastructure costs for EC2, EBS storage, and data transfer are billed separately from this software rate.
Top-of-mind questions for buyers
What hardware do I get for the hourly software charge on the t3.medium instance?
The t3.medium rate covers software running on that instance type, sized at 4 GiB memory minimum with 24 GiB root storage. These are starting minimums, not throughput benchmarks. Access is through a private HTTPS connection on port 8443. You provide the EC2 instance in your own AWS account.
Does the hourly charge keep accruing if I stop or terminate the instance?
The hourly software charge applies only while the instance runs. Stopping or terminating the instance stops that charge. Retained EBS volumes and other AWS resources can still incur charges even after you stop the instance, so terminate unused resources to control total cost.
Does the hourly software rate include a trial period or any annual commitment?
No. There is no bundled software trial and no annual term with this listing. You pay the hourly software rate per running instance-hour, with no upfront commitment. EC2, EBS, and data transfer are billed separately by AWS.
docs.softwaresushi.com
Helpful?
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) are billed by AWS and are not eligible for refund by us.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Whisper CPU 0.1.11 on Ubuntu 24.04. Rebuilt the host Brotli packages to the Ubuntu fixed version for CVE-2026-111497. English and Spanish CPU transcription with the pinned multilingual small model remains. Fresh EC2 boot and installed demo smoke passed. Broader native compiled-component coverage remains unverified; this version does not claim full Software Sushi security qualification.
Additional details
Usage instructions
Launch t3.medium with at least 24 GiB encrypted gp3 root storage and IMDSv2; keep inbound application ports closed. 2. Connect with Session Manager as ubuntu or SSH restricted to your administrative CIDR. 3. Wait for cloud-init and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. 4. Forward HTTPS port 8443 with Session Manager or an SSH tunnel; follow the private access instructions and first request in https://docs.softwaresushi.com/whisper-cpu/. 5. Back up customer data before replacing the instance. EC2, EBS and data transfer are billed separately from software.
Software Sushi provides installation and configuration guidance for this image. Contact info@softwaresushi.com with your product version and reproduction steps; never send keys or private configuration. Guaranteed response times require a separate agreement. This offer does not include upstream project support.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Generate natural English speech from text with Chatterbox Nano on CPU, in the voice of a short sample you provide. This Ubuntu 24.04 AMI runs a private, token-protected speech service in your own AWS account, so you can create narration and voice prompts without sending text or voice data to a third-party service.
Pre-installed and security-hardened OpenClaw AI agent AMI. Launch an EC2 instance, add your credentials, and start using your agent. Ready to configure out of the box.
Docling converts PDF and DOCX files into clean Markdown and structured JSON for search, RAG pipelines and data extraction. This Ubuntu 24.04 AMI runs Docling on CPU behind a private HTTPS API with per-instance TLS. Processing stays on the instance, with no model API key and no remote services.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.