Platform Preview

We want to be straight about what AMBIE is today vs. what AMBIE will be.

AMBIE is a platform for acoustic intelligence — the goal is 90-95% transcription accuracy in environments where traditional ASR fails (ICUs, manufacturing floors, busy restaurants, court reporting). The proprietary models that deliver that accuracy are in development and will be released in 2027.

In the meantime, the API itself is live. The endpoint shapes, auth, retry behavior, webhook signatures, SDKs, billing, and developer experience are stable enough to integrate today. Behind the scenes the inference is currently served by commodity off-the-shelf models. We’re honest about that.

What’s under the hood today

Endpoint	Today	2027 (proprietary)
Transcribe	Deepgram Nova-3 / OpenAI Whisper	AMBIE Acoustic-Intelligence v1
Translate	Llama 3.1 70B	No swap planned
TTS (Aura 2)	Deepgram Aura 2	AMBIE-Voice (likely)
TTS (MeloTTS)	MeloTTS via Cloudflare AI	No swap planned
Embeddings	BGE family	No swap planned
Rerank	BGE Reranker	No swap planned
Sentiment	DistilBERT-SST-2	No swap planned
Summarize	BART	No swap planned
Moderate	Llama Guard 3	No swap planned
Detect language	small classifier	No swap planned

The transcription and TTS endpoints are where the actual AMBIE intelligence will land. Translation, embeddings, rerank, sentiment, summarize, moderate, and detect-language are utility endpoints we offer because they’re commonly chained with audio workflows; we don’t plan proprietary versions of those.

Why integrate now?

• Stable API surface. The endpoint shapes, auth, retry, webhook contract, and SDKs aren’t changing when the proprietary models swap in. Your integration carries forward.
• Same code, new engine in 2027. When AMBIE Acoustic-Intelligence v1 ships, the same engine: "ambie" param will route to it. Your code stays the same; transcription quality jumps.
• Founder-friendly preview. $5 trial credit, $1/day cap during trial, no subscription, monthly invoicing. See pricing.

What will change at GA?

The transcribe endpoint will gain an engine: "ambie" option (and likely default to it). Today’s deepgram and whisper options stay available for cost-sensitive workloads.

Pricing for the AMBIE engine will be announced before GA and will reflect the proprietary R&D and serving costs of a model purpose-built for noisy environments. Today’s rates are passthrough-COGS-based and apply only to the preview engines (deepgram, whisper); plan accordingly when budgeting for the AMBIE engine swap.

Email cisco@ambie.ai if you’re an early-access candidate (high audio volume, noisy-environment use case, willingness to share feedback during beta).

AMBIE is a product of RoamingPigs, Inc. (Las Vegas, NV).