RRepoGEO

REPOGEO REPORT · LITE

modal-labs/quillman

Default branch main · commit 5e4bd7e5 · scanned 5/20/2026, 4:58:02 AM

GitHub: 1,205 stars · 157 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface modal-labs/quillman, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Clarify the README's opening statement to emphasize it's a complete application example for real-time voice chat

    Why:

    CURRENT
    # QuiLLMan: Voice Chat with Moshi

A complete voice chat app powered by a speech-to-speech language model and bidirectional streaming.
    COPY-PASTE FIX
    # QuiLLMan: Real-time Voice Chat Application Example

This repository presents a complete, real-time voice chat application example, demonstrating how to build an AI-powered speech-to-speech conversational agent. It uses Kyutai Lab's Moshi model and bidirectional streaming to achieve near-instantaneous responses, serving as a robust starting point and playground for developers building their own language model-based voice applications.
  • mediumabout#2
    Update the repository description to be more specific about its nature as an example

    Why:

    CURRENT
    A voice chat app
    COPY-PASTE FIX
    A complete, real-time voice chat application example powered by AI speech-to-speech models and bidirectional streaming.
  • mediumtopics#3
    Expand repository topics to include 'real-time' and 'conversational-ai'

    Why:

    CURRENT
    ai, language-model, python, serverless, speech-recognition, speech-to-text
    COPY-PASTE FIX
    ai, language-model, python, serverless, speech-recognition, speech-to-text, real-time, conversational-ai, voice-chat

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface modal-labs/quillman
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
AssemblyAI
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. AssemblyAI · recommended 2×
  2. Amazon Polly · recommended 2×
  3. Azure/azure-sdk-for-python · recommended 2×
  4. Deepgram · recommended 1×
  5. OpenAI Whisper · recommended 1×
  • CATEGORY QUERY
    How to build a real-time voice chat application using AI speech models?
    you: not recommended
    AI recommended (in order):
    1. Deepgram
    2. AssemblyAI
    3. OpenAI Whisper
    4. Google Cloud Speech-to-Text / Text-to-Speech
    5. Amazon Polly
    6. WebRTC
    7. Socket.IO

    AI recommended 7 alternatives but never named modal-labs/quillman. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a Python example for serverless speech-to-speech language model integration.
    you: not recommended
    AI recommended (in order):
    1. AWS Lambda
    2. Amazon Transcribe
    3. Anthropic Claude
    4. OpenAI GPT-4
    5. Amazon Polly
    6. boto3 (boto/boto3)
    7. anthropic (anthropics/anthropic-python)
    8. openai (openai/openai-python)
    9. Google Cloud Functions
    10. Google Cloud Storage
    11. Google Cloud Speech-to-Text
    12. Google Gemini
    13. Google Cloud Text-to-Speech
    14. google-cloud-storage (googleapis/python-storage)
    15. google-cloud-speech (googleapis/python-speech)
    16. google-cloud-texttospeech (googleapis/python-texttospeech)
    17. google-generativeai (google/generative-ai-python)
    18. Azure Functions
    19. Azure Blob Storage
    20. Azure AI Speech
    21. Azure OpenAI Service
    22. azure-functions (Azure/azure-functions-python-worker)
    23. azure-storage-blob (Azure/azure-sdk-for-python)
    24. azure-cognitiveservices-speech (Azure/azure-sdk-for-python)
    25. Vercel Serverless Functions
    26. Netlify Functions
    27. AssemblyAI
    28. ElevenLabs
    29. requests (psf/requests)
    30. Whisper (openai/whisper)
    31. Hugging Face Inference API
    32. Llama 3 (meta-llama/llama3)
    33. Bark (suno-ai/bark)

    AI recommended 33 alternatives but never named modal-labs/quillman. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of modal-labs/quillman?
    pass
    AI named modal-labs/quillman explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts modal-labs/quillman in production, what risks or prerequisites should they evaluate first?
    pass
    AI named modal-labs/quillman explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo modal-labs/quillman solve, and who is the primary audience?
    pass
    AI named modal-labs/quillman explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of modal-labs/quillman. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/modal-labs/quillman.svg)](https://repogeo.com/en/r/modal-labs/quillman)
HTML
<a href="https://repogeo.com/en/r/modal-labs/quillman"><img src="https://repogeo.com/badge/modal-labs/quillman.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

modal-labs/quillman — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite