About — Editorial AI studio · 2026

Onde is the idea that an AI podcast can be truly editorial.

Not a robotic reader of articles. Not a generic summariser. An on-demand audio studio that turns French-speaking curiosity into a directed listening experience — with editorial controls, signature voices and an EU compliance layer baked in.

Designed in France · Hosted in the EU · Native French-first

Our mission

Turn French-speaking curiosity into a personalised listening experience.

Onde exists because audio production is the bottleneck of knowledge transmission. Articles get scrolled past. Reports get archived. Podcasts get scheduled but rarely match the exact topic, angle and duration you need today.

We do not summarise Wikipedia. We produce a directed episode: a real script, a real cast of voices, a real editorial intent. You stay the editor-in-chief — we run the studio.

Why French-first

80M+ French speakers under-served by US tools.

NotebookLM, ElevenLabs GenFM and most American podcast generators were designed for English ears first, with French added later as a translated locale. Onde was built the other way around — and it shows.

Native French voices

ElevenLabs voices hand-picked for FR prosody and liaison accuracy, under commercial license.

FR-optimised LLM prompts

Prompts written in French, French first-name bank tagged by tone and region, no English pivot.

French cultural context

Pension reform, EU AI Act, French jurisprudence — the model knows the references that matter for a French-speaking audience.

Signature jingles for the FR ear

7 narrative genres with intro/outro jingles produced for a French audience — not stock libraries.

Editorial guardrails

Six non-negotiables, baked into the pipeline.

Trust isn't a marketing claim. It's a stack of technical decisions you can verify in the audio file you download.

Embedded EU AI Act disclaimer

Every episode embeds a clear vocal notice stating it was produced with artificial intelligence. Not optional, not editable.

SHA-256 ID3 watermark

The MP3 file embeds a SHA-256 topic hash, episode ID, user ID and timestamp. End-to-end traceability without breaking the standard format.

Real-person blocklist

An LLM filter blocks impersonation of politicians, journalists, executives, or reproduction of media brands (BFM, France Inter, etc.) before generation even starts.

Licensed voices only

Commercial ElevenLabs pool, never any non-consented cloning. Opt-in voice cloning will arrive with signed written consent, not before.

Anti-AI-tics in scripts

Automatic penalty on "Of course!", "Absolutely!", "Indeed,", "Great question", "Isn't it?". The adversarial scorer rejects scripts that feel robotic.

Rigorous Mode with traced sources

On sensitive topics (news, health, law, science, geopolitics), a Haiku classifier triggers a Sonnet agent equipped with web_search. Sources listed in the editorial pack.

Our stack

The bricks that hold the studio together.

No technical posturing — just the choices that matter, and why we made them. The whole pipeline runs on European infrastructure.

Language model

Anthropic Claude — Haiku 4.5 (≤ 15 min) · Sonnet 4.6 (long form)

Haiku for speed and cost on short formats, Sonnet for narrative consistency on long-form episodes. The right model for the right cognitive budget.

Voice synthesis

ElevenLabs eleven_v3

The most natural voice model on the market in 2026. French voices hand-picked for prosodic consistency and accurate liaisons.

Audio assembly

ffmpeg with loudnorm −16 LUFS · TP −1.5 · LRA 11

Spotify, Apple Podcasts, Deezer standard. Distribution-ready out of the pipeline, no post-mortem touch-up required.

Object storage

Cloudflare R2

Zero egress fees, European infrastructure, low latency. Native choice for streamed audio.

Database

PostgreSQL via Supabase (EU region)

Data stored in the European Union. GDPR compliance by location, not by contractual workaround.

Web application

Next.js 16 · Vercel · EU hosting

Modern stack, European deployment, optimised runtime. No technical posturing: just the bricks that make the service fast and legible.

Editorial combinatorial

1,183 editorial directions for one topic.

7 formats×13 tones×13 angles=1 183

The same topic can become a pedagogical lecture or a documentary thriller, a neutral piece or a devil's advocate debate. That's a massive combinatorial space — and it's what turns the user into a director rather than a spectator.

Our approach vs the rest

Four product decisions, four hills we'll die on.

  • Native FR generation, not translated

    Prompts are written in French, voices are native French, jingles are produced for the FR ear. No English pivot along the way.

  • The combinatorial, not the single format

    7 formats × 13 tones × 13 angles = 1,183 possible editorial directions. The same topic can become a teaching lecture or a documentary thriller.

  • AI owned, not hidden

    Mandatory vocal disclaimer, SHA-256 ID3 watermark, pre-generation moderation. Transparency is a product choice, not a concession.

  • Broadcast quality, not robotic

    Loudnorm −16 LUFS, signature jingles per genre, controlled transitions. The episode must hold up on headphones, in the car, on speakers.

Compliance commitments

Five things we owe you.

Compliance isn't a checklist filed once a year. It's a daily operating constraint that shapes every product decision.

  • GDPR compliance by data localisation in the European Union (Supabase EU + Cloudflare R2 EU).
  • EU AI Act compliance: mandatory inline audio disclaimer, SHA-256 ID3 watermark on every MP3.
  • No reselling of user data to model providers. No fine-tuning on submitted topics.
  • Editorial ownership for users: every generated episode belongs to its author, within the scope of their plan.
  • Audit-ready: moderation events logged in DB, versioned blocklist, per-episode quality scoring trace.

Public roadmap

Where we are going, in writing.

We publish our priorities so you can hold us to them. Dates are targets, not contractual promises.

  1. Q3 2026

    EN locale live · Opt-in voice cloning

    English-speaking market opens with dedicated EN voices (no FR translation). Voice cloning with signed written consent for Pro creators.

  2. Q4 2026

    B2B API · LMS integrations for the Team plan

    Documented REST API + webhooks to integrate Onde into an internal LMS (Cornerstone, Docebo, 360Learning). SAML / SCIM provisioning available on Enterprise.

  3. 2027

    Curated RAG corpus · B2B white-label

    Reinforced grounding via curated corpus (Wikipedia + INSEE + Eurostat). White-label for large accounts and EdTech platforms.

Now you know who we are.

The studio is open. Free-form topic, editorial controls, an episode in under 3 minutes. 15 free credits to test, then €14 a month if you stay.

Contact us: hello@ondeaudio.com