INGEST
Media Ingestion
Researchers can upload recorded audio and video materials from mobile devices into a unified workflow.
- Audio and video upload
- Built for corpus organization
CORPUSSPARK INTRO
About CorpusSpark
CorpusSpark is a multimodal transcription and annotation platform built on AI technology, currently focused on reducing the cost and time of corpus processing. Researchers can upload recorded audio and video materials from mobile devices, and the platform combines speaker recognition with automatic transcription to complete the first round of corpus organization.
The platform supports synchronized viewing of transcript text, audio/video, and aligned timelines. After manual review and annotation, the results can be exported in formats compatible with the TALKBANK clan workflow for subsequent analysis, archiving, and research use.
CorpusSpark currently supports iPhone, iPad, and Mac with Apple silicon. It is designed to be easy to use for both experienced researchers and first-time users. More feature details and updates are available through the CorpusSpark official account.
WeChat
CorpusSpark Updates
Follow the official account for product updates and feature notes.
Key Points
- Supports iPhone, iPad, and Mac with Apple silicon
- Supports speaker differentiation and timeline alignment
- Supports TALKBANK / clan export
- Follow the official account for more details
Article
More Details
Additional notes on automatic processing, supported devices, and research use.
Its machine transcription capability can quickly handle labor-intensive preprocessing tasks such as content transcription, speaker labeling, and timeline alignment. Researchers can then continue with review, label enrichment, and more detailed transcription work aligned with their research goals.
CorpusSpark starts from the needs of linguistics research while balancing efficiency, accuracy, accessibility, and cost. It is also intended to support high-quality corpus co-creation, research data verification, and downstream applications.
Automatic transcription and speaker recognition
Timeline alignment across text and media
Manual review and label editing
Structured result export
Capabilities
Core Capabilities
The CorpusSpark platform organizes its core features around the multimodal corpus processing workflow.
ASR
Automatic Transcription
Automatic transcription handles repetitive preprocessing work and quickly produces an initial draft.
- Fast first-pass transcript
- Lower manual effort
SPK
Speaker Differentiation
Speaker recognition helps distinguish speakers and produce a clearer conversational structure.
- Speaker recognition support
- Automatic turn organization
SYNC
Timeline-Synced Review
Text, audio/video, and aligned timelines can be reviewed together for easier replay and verification.
- Replay with synchronization
- Timeline-aligned viewing
EDIT
Review & Label Editing
Users can revise machine results, update speaker labels, and add more detailed annotations.
- Text and label editing
- Supports finer transcription work
EXPORT
Structured Export
After review, results can be exported in TALKBANK/clan-compatible formats for analysis and archiving.
- TALKBANK / clan compatible
- Ready for research workflows
Workflow
Processing Workflow
A clear process from data ingestion and automatic processing to human review and structured export.
Ingestion
Audio, video, and text are brought into one workflow.
Start from a unified pipeline.
Automatic Processing
Transcription, analysis, and preprocessing are executed.
Improve front-end efficiency.
Human Review
Annotation review and quality checks refine the results.
Keep outputs consistent.
Structured Export
Results are exported in standardized formats.
Ready for training and integration.