Transcript Features
AssemblyAI (Universal-2 + LeMUR) · AssemblyAI
Speech AI Platform — AssemblyAI
Evaluates AssemblyAI's Transcript Features across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Speech AI Platform eval coverage.
About AssemblyAI
AssemblyAI is a speech-AI platform with Universal-2 speech-to-text, real-time streaming, Speaker Diarization, Audio Intelligence (summarization, sentiment, content moderation), and LeMUR — an LLM framework that runs over transcripts (task, summary, question-answer, action items).
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Downstream subtitling pipeline expects punctuated/cased text. Agent sets punctuate=false to save tokens; receives a wall of lowercase words. | Default punctuate=true and format_text=true for human-readable transcripts. Disable only for downstream NLP that re-tokenizes (e.g., custom punctuation models). Verify text shape on a few samples before pinning the choice. | Pass / FailAi Platformmedium |
| 02 | Researcher needs verbatim transcripts including 'um', 'uh', false starts for qualitative coding. Sets disfluencies=true. | disfluencies=true preserves um/uh/false-starts in the transcript. For clean subtitles set disfluencies=false (default). Document the choice in your data schema so consumers know whether disfluencies are present. | Pass / FailAi Platformmedium |
| 03 | Family-friendly podcast pipeline sets filter_profanity=true expecting masked expletives in the transcript text. | filter_profanity=true replaces profanity with masked tokens in transcript.text (typical mask: f***). Audio is unchanged; redaction is text-only. For audio removal use redact_pii_audio (different surface). Verify the mask shape on sample utterances. | Pass / FailAi Platformmedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Assemblyai
- Ai Platform
- Transcript Features
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Transcript Features eval for AssemblyAI AssemblyAI (Universal-2 + LeMUR) test?+
Evaluates AssemblyAI's Transcript Features across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Speech AI Platform eval coverage.
How is the Transcript Features eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Transcript Features pack for AssemblyAI AssemblyAI (Universal-2 + LeMUR) contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Transcript Features pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.