Summary
maple-proxy should expose an OpenAI-compatible /v1/audio/transcriptions endpoint, enabling audio transcription via whisper-large-v3 through the proxy.
Blocked by
This is blocked on the opensecret Rust SDK adding transcription support:
OpenSecretCloud/opensecret#140
Once OpenSecretClient has a create_transcription() method, maple-proxy needs a new route that:
- Accepts
multipart/form-data with an audio file, model name, and optional params (language, response_format)
- Calls the new
OpenSecretClient::create_transcription() method
- Returns the transcription response
Context
The Maple backend already lists whisper-large-v3 as an available model, but there's no way to use it through the proxy today.
Summary
maple-proxyshould expose an OpenAI-compatible/v1/audio/transcriptionsendpoint, enabling audio transcription viawhisper-large-v3through the proxy.Blocked by
This is blocked on the
opensecretRust SDK adding transcription support:OpenSecretCloud/opensecret#140
Once
OpenSecretClienthas acreate_transcription()method,maple-proxyneeds a new route that:multipart/form-datawith an audio file, model name, and optional params (language, response_format)OpenSecretClient::create_transcription()methodContext
The Maple backend already lists
whisper-large-v3as an available model, but there's no way to use it through the proxy today.