Loading
transcribe-small
Transcribes uploaded audio - meetings, voice notes, calls, dictation - into text with timestamps and language detection; answers the OpenAI-compatible /v1/audio/transcriptions endpoint (never chat).
Requests per day this target answered on this deployment, with the cost line.
No requests yet. Route something from the playground to see usage here.
Domains the signal layer detected on requests that ended here.
No routed requests yet. Declared domains: General, Customer Support.
Hard stops enforced before scoring.
This tool is not executed by the platform. Ask the router for a decision restricted to kinds=["tool"] and dispatch the winner in your own stack; send feedback afterwards so the learners improve.
curl https://api.opensmartroute.ai/api/v1/route \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "Transcribe the attached audio file meeting.mp3.", "kinds": ["tool"], "top_k": 3}'
# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of tool targets happens in your stack.import httpx
r = httpx.post(
"https://api.opensmartroute.ai/api/v1/route",
headers={"Authorization": "Bearer osr_live_..."},
json={"text": "Transcribe the attached audio file meeting.mp3.", "kinds": ["tool"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]]) # e.g. transcribe-small first when it fitsExamples the similarity strategy matches against.