Loading
speak-small
Reads text aloud in a natural voice and returns audio (mp3, opus, wav ...); answers the OpenAI-compatible /v1/audio/speech 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, Marketing.
Hard stops enforced before scoring.
Pin this target with model="speak-small", or send a candidate list and let the router choose and fall back.
curl https://api.opensmartroute.ai/v1/chat/completions \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "speak-small", "messages": [{"role": "user", "content": "Read this paragraph aloud."}]}'from openai import OpenAI
client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
model="speak-small", # pin this target, or "auto" to let the router choose
messages=[{"role": "user", "content": "Read this paragraph aloud."}],
extra_body={"models": ["speak-small", "auto"]}, # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)Examples the similarity strategy matches against.