AudioWrench Audio Tools
dev.workers.tarsanbeats.audiowrench-mcp/audio-tools · v0.1.0-beta.1 · MCP 2026-07-28
Reverse or trim selected WAV files, or transcribe WAV to TXT/SRT with Whisper Tiny and Base.
Reachability
reachable
checked 2026-11-21 05:35 UTC
Registry status active
Tools pinned 23
aad0710f3d01
Tools last changed
unchanged since first capture 2026-11-17
Provenance
Registry namespace dev.workers.tarsanbeats.audiowrench-mcp
(domain verified by the official registry)
Website
https://audiowrench.com/
Remote endpoints
https://audiowrench-mcp.tarsanbeats.workers.dev/mcp (streamable-http)
Observed changes
| When (UTC) | Event | Detail |
|---|---|---|
| 2026-11-17 05:30 | first capture | 23 tools pinned |
Pinned tool definitions (23)
| Tool | Description |
|---|---|
| aw.status | Read public beta coverage and service limits. |
| aw.catalog | Find supported public beta workflows by task. |
| aw.session.open | Create a private15-minute remote processing session. No local installation and no personal input is sent by opening it. |
| aw.session.close | Explicitly revoke this transient remote session and remove its remote copies; original disk files are never touched. |
| aw.jobs.list | Statuses for this session only, without selected audio or private URLs. |
| aw.jobs.cancel | Retire active work AND in-flight uploads that have not committed. Completed immutable inputs/artifacts are not deleted. Stable upload UUID/operationId reconcile committed receipts. Bounded32 cancellation requests remain available after... |
| aw.artifact.verify | Re-read authenticated chunks and hash an actual current-session artifact; return metadata, never audio bytes. |
| aw.transfer.guide | Explicit native MCP file-transfer contract, bounds and client-history privacy. Discovery does not read your disk. |
| aw.input.begin | Reserve bounded encrypted staging for one explicitly selected file. NO source publication or job retirement until validated commit;2 pending/max24 identities. |
| aw.input.write_chunk | Append one exact canonical-base6432768-byte chunk (last=remainder) to this attempt in order. Exact retries reconcile; binary bodies may reach client/model history. |
| aw.input.status | Resume this exact transfer attempt without returning any selected bytes. Retired/complete state is explicit. |
| aw.input.commit | Verify ALL staged bytes/hash/original format and atomically publish one current immutable input. Exact completed retries recover its receipt; invalid/partial data never retires a job. |
| aw.input.abort | Discard this pending transfer attempt only; does not cancel the current processing job or delete a completed immutable input. Use jobs.cancel for all pending stages. |
| aw.artifact.read_chunk | Return one bounded binary embedded resource from this session artifact, plus range/whole-file hashes. Reassemble and hash ALL bytes. Not disk-save or whole-file verification from one range. |
| aw.speech.whisper_encode_step | Prepare the exact original Tiny or Base encoder in separate bounded calls: two for Tiny, three for Base. Begin with the accepted WAV source and no continuation. While status is encoder-pending, supply its opaque continuation with the... |
| aw.speech.whisper_decode_step | Explicit bounded continuation of the REAL original Tiny/Base decoder for a whole accepted selected WAV. First call uses the SAME-session original encoder handle and null continuation. A nonterminal step returns only an opaque encrypted... |
| aw.speech.transcribe | Original Tiny/Base whole-file transcription with a CURRENT shared transcript. Explicit SAME-session original encoder handle required; Run at most64 original decoder steps for Tiny or32 for Base per explicit call, with identical... |
| aw.speech.transcript.read | Read CURRENT accepted original transcript segments and exact time values, explicitly, in bounded pages. Null transcript selects current state; an expected handle fences stale/cleared/newer results. No model I/O, recording or unfinished... |
| aw.speech.transcript.export | Export the CURRENT accepted transcript as exact original TXT or SRT, with NO model call. Same original serializers/timestamp fallback/CRLF, verified immutable header-auth artifact. Explicit current handle and UUID; replay requires same... |
| aw.speech.transcript.clear | Explicitly clear the EXPECTED CURRENT shared transcript only and leave an empty generation, matching original Clear semantics. Null succeeds only when no current state exists; a stale handle cannot clear a newer result. Does NOT cancel... |
| aw.speech.whisper_export_txt | Export the original TXT from a complete current-session SRT produced by aw.speech.whisper_decode_step, without invoking the model again. Only a verified original decoder SRT artifact in the same active source revision is accepted; no... |
| aw.audio.reverse | Reverse every channel with the actual AudioWrench core; verified new PCM WAV. |
| aw.audio.trim | Copy the current source-frame interval using the unchanged core floor-to-frame semantics. |
Get alerted when this changes.
Email the moment dev.workers.tarsanbeats.audiowrench-mcp/audio-tools drifts, dies, or revives.
Status badge
[](https://toolpin.dev/servers/dev.workers.tarsanbeats.audiowrench-mcp/audio-tools)
Maintain this server? Add the badge to your README. It links your users to this live status page.