Tonn Post-Production SDK and API brings professional-grade audio processing to your workflow via a purpose-built post-production pipeline - dialogue-first, delivery-spec compliant, and built for the formats that broadcasters and platforms demand.
Integrate AI-powered dialogue enhancement, automatic loudness compliance, ADR matching and sidechain ducking into your platform with an SDK or API integration.
Scalable
Power your platform with RoEx’s trusted technology, with over five million processed tracks since 2023.
Rapid
Achieve broadcast-compliant audio in minutes with Tonn’s on-device or cloud processing.
Tailored
Dynamic processing to suit your content type - dialogue, music, SFX, ambience, foley and more.
Responsible
We never train on your audio - your content stays yours. Built on pioneering research from Queen Mary University of London.
Dialogue Enhancement
Deliver clear, intelligible speech across every content type.
Three processing modes - Preserve, Enhance, and AD Enhanced - tuned for natural sound, standard broadcast, and commercial voiceover respectively. The Tonn engine performs noise floor detection, frequency balance assessment, and clipping analysis before applying any processing.
Delivery Format Compliance
Correct loudness. Compliant delivery.
Seven built-in delivery presets calibrated to Film, TV, Streaming, YouTube, Broadcast, Ad Mix, and Podcast. Each output includes a full compliance report covering programme loudness, dialogue loudness, true peak, and LRA - ready to feed into your QC pipeline.
ADR Matching
Make re-recorded dialogue sit naturally against original location sound.
The DialogueMatcher analyses the frequency response, dynamics, timbre, and reverb characteristics of the original recording, then applies matching processing to the ADR take. Similarity scores are returned programmatically so you can verify the match in your pipeline.
Automatic Sidechain Ducking
Keep dialogue front and centre without manual volume rides.
Background audio - music, SFX, ambience - automatically ducks when dialogue is detected. Five presets cover common scenarios, from subtle -6 dB reductions through to -20 dB cuts for narration over score. Multitrack ducking lets a single dialogue sidechain control multiple background tracks simultaneously.
Audio Cleanup
Remove noise and artefacts from location recordings, ADR, and voiceover.
AI-powered noise reduction clears background hiss, hum, room tone, and microphone bleed from individual audio tracks, delivering pristine audio that sits cleanly in the final mix.
Processed Stems Output
Export individually processed stems alongside your final mix for QC, revision, and downstream editorial work.
How It Works
Three steps from integration to compliant output.
Integrate via API or SDK Connect to the Tonn API or add the C++ SDK directly to your application. Full documentation, example applications, and JSON configuration templates for common workflows are available to get you started quickly.
Configure your pipeline Select your track types, processing modes, and delivery format preset. Tonn handles the analysis, processing, compliance checking, and output automatically.
Process and receive results Submit your audio and receive processed output alongside a full compliance report covering programme loudness, true peak, LRA, and dialogue loudness - ready to feed directly into your QC pipeline or editorial workflow.
We never train on your audio. Ownership stays with you.
Files are processed privately; you control downloads and deletion.
Input: WAV/AIFF/MP3, mono or stereo, 44.1-96 kHz, 16/24/32-bit
Output: WAV (default), with optional stem exports per processed track
Processing: Noise reduction, dialogue enhancement, loudness normalisation, true-peak limiting, ADR matching, sidechain ducking and delivery format compliance
Delivery: Results returned via API response or webhook; processed files available for immediate download or pipeline ingestion
Pay-per-use licensing via the Tonn API Portal (see Pricing).
Commercial usage supported; all rights retained by you.
Contact us for SDK licensing for enterprise and broadcast via SDK.
Got Questions?
Frequently asked
questions
What content types does the Tonn API support?
Which delivery standards does Tonn target?
Does the API handle multitrack audio?
How does ADR matching work?
Is the processing non-destructive?
How do I get access?
Ready to integrate AI audio post-production into your platform?
Begin building today with the cloud-based API, or contact RoEx to enquire about the offline SDK.
For larger organisations or high-volume needs, we offer a customised plan tailored to your usage and business size, including dedicated support and service level agreements.
Tailored sound profiles and compliance needs can be built to spec for organizations with scaled audio solution requirements.
Resources