Hanzo

Audio

Package ai is Hanzo AI — the model API on /v1 (/v1/chat/completions, /v1/messages, /v1/models and the rest of hanzoai/ai's surface) — mounted into a cloud binary with the money, ingest and telemetry…

Package ai is Hanzo AI — the model API on /v1 (/v1/chat/completions, /v1/messages, /v1/models and the rest of hanzoai/ai's surface) — mounted into a cloud binary with the money, ingest and telemetry callbacks cloud BUILDS but cannot INSTALL.

Base URLhttps://api.hanzo.ai
Operations4
AuthAuthorization: Bearer $HANZO_API_KEY

audio

POST /v1/audio/foley

Serves the generative audio verbs — /v1/audio/voice (TTS), /music, /foley — that the Zen family serves natively. It resolves the SKU and, for a Zen model, forwards to zen's matching verb billed per call at the discovered price. These verbs are Zen-native; a non-Zen model is rejected.

POST /v1/audio/music

Serves the generative audio verbs — /v1/audio/voice (TTS), /music, /foley — that the Zen family serves natively. It resolves the SKU and, for a Zen model, forwards to zen's matching verb billed per call at the discovered price. These verbs are Zen-native; a non-Zen model is rejected.

POST /v1/audio/speech

The OpenAI-compatible TTS endpoint (POST /v1/audio/speech). It authenticates the caller, resolves model to its TTS provider (the SAME model-route resolution the chat/images/video endpoints use — so a BYO node registered as a TTS provider works transparently), synthesizes the audio, and streams the bytes back. One code path, OpenAI-shaped, no store/message coupling (unlike the legacy /v1/generate-text-to-speech-audio which is bound to a chat store).

POST /v1/audio/voice

Serves the generative audio verbs — /v1/audio/voice (TTS), /music, /foley — that the Zen family serves natively. It resolves the SKU and, for a Zen model, forwards to zen's matching verb billed per call at the discovered price. These verbs are Zen-native; a non-Zen model is rejected.


All Hanzo APIs · Interactive reference

How is this guide?

On this page