Twelve close open-source candidates, none documents all six spoken-English coaching features; the best reach 5 of 6

Asked (summary):Find, list and factually compare all ready-to-use or easily deployable, fully open-source all-in-one applications for spoken-English practice with AI coaching, ASR/error detection, corrective practice, progress tracking, drills and conversation; document A–D facts, compare six core features, list exact sources and explain exclusions — only verifiable public facts, "Not documented / Not present" for unsupported claims, and no libraries or fragmented components.

The scan normalized 62 named candidate projects and yielded 12 close application candidates with detailed repository documentation; the rest were components, unrelated same-name projects, or unverifiable listings. All facts come from indexed official repository pages and were last checked 2026-09-11. Absent fields are shown as "Not documented / Not present"; README TODO items are not counted as current features.

Findings

Strict six-feature comparison

For "Active correction + forced correct speech": forced repetition is not documented for any tool except Mimora, which states a repeat-until-satisfied phrase loop; Babblr documents level-appropriate corrections but no forced retry. Generic feedback is not counted as forced correction.

Tool	License	ASR	Error detection	Active correction + forced retry	Progress	Guided drills	Conversation	Score	Version / release / activity	Source

A–D fact blocks per candidate

Exclusions, factually

Sources

Method: catalogue built from indexed official GitHub repository pages, checked 2026-09-11. 62 normalized candidate projects scanned; 12 detailed candidates compared row by row on six core features (ASR, error detection, active correction with forced retry, progress tracking, guided drills, conversation); a score counts features supported by repository text only. The fetched README pages exposed no tagged version, release date or last-commit date for the 12 detailed candidates — shown as not documented, not as abandoned. Stack and limitation texts truncated for space; exclusion evidence limited to exact-match repositories.

This report was generated automatically by Keenable SELECT at a user's request, from publicly available web sources linked herein. Keenable does not review, verify, or endorse its contents and makes no representation as to accuracy, completeness, or timeliness; AI-based extraction may contain errors. Nothing in this report is investment, legal, financial, or other professional advice. All trademarks and referenced content remain the property of their respective owners; no affiliation or endorsement is implied. To report an error, rights concern, or request removal: legal@keenable.ai.