{
 "schema_version": 1,
 "generated": "2026-10-26",
 "id": "nari-labs-nari-qwen3-tts--pick-latency-or-throughput-profile",
 "repo": "nari-labs/nari-qwen3-tts",
 "repo_url": "https://github.com/nari-labs/nari-qwen3-tts",
 "repo_slug": "nari-labs-nari-qwen3-tts",
 "title": "Choose a latency or throughput profile for load",
 "page_title": "How to choose a latency or throughput profile for load with Nari Qwen3 TTS",
 "summary": "Switch between ttfa, balanced, and throughput profiles to match a latency target or a request volume.",
 "who": "A platform engineer sizing a speech service that must meet a first-audio latency target or handle heavy batch load on one H100.",
 "problem": "One fixed setting cannot favor both fast first audio for interactive users and high aggregate throughput for batch jobs.",
 "outcome": "A chosen profile and a repeatable server start command that matches the workload.",
 "steps": [
  "Install the environment with `uv sync --frozen --extra codec --extra cuda --extra serving`.",
  "Start the server with a profile: `uv run --frozen nari-qwen3-tts-server --profile ttfa` for latency, or `--profile throughput` for aggregate load. (inferred, check the README)",
  "Check readiness with `curl --fail http://127.0.0.1:8000/ready` before sending traffic.",
  "Record the time to first audio and the request rate for each profile, then keep the profile that meets the target."
 ],
 "agent_prompt": "In the nari-labs/nari-qwen3-tts repo, start the server with the <profile> profile (ttfa, balanced, or throughput) and send a fixed set of test requests to `/v1/audio/speech`. Expected output: a short table of time to first audio and completed requests for each profile tested. Verify that each run started only after `/ready` returned success.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "The README gives the profile purposes but no numeric targets for each one, so any measured figures must come from the user's own runs on their hardware.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "A Linux x86_64 host with an NVIDIA H100 GPU",
  "NVIDIA Container Toolkit and a driver compatible with CUDA 13.0 (for Docker)",
  "Docker, or uv with Python and the system packages build-essential, libsndfile1, and sox",
  "A Hugging Face token (HF_TOKEN) if the model files need to be downloaded"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/nari-labs-nari-qwen3-tts/pick-latency-or-throughput-profile/",
 "md": "https://dedupedai.com/use-cases/nari-labs-nari-qwen3-tts/pick-latency-or-throughput-profile/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/nari-labs-nari-qwen3-tts--pick-latency-or-throughput-profile.json",
 "api_version": "v1"
}