
tts-tools
Browser-based listening pages and a voice-seed library for comparing and keeping TTS voice clips.
- version
- 1.0.0
- GitHub stars
- 32
What it does
- Adds the
listening-pageskill for side-by-side clip comparison with choices saved as JSON - Covers seven templates:
voice-pick,ab-original,eq-mix,checkpoint-compare,term-check,pairwise, andblind-ab - Runs a local server on 127.0.0.1 that rejects cross-origin writes and autosaves each choice
- Adds the
voice-seedsskill to keep reference voice clips with full provenance in a git library
TTS listening pages: compare clips side by side, save picks. Voice candidates, original vs processed, EQ chains, checkpoints, blind A/B; choices saved as JSON.
Add marketplace
/plugin marketplace add danielrosehill/Claude-Code-PluginsRun it inside Claude Code once, then install the plugin below.
Install
/plugin install tts-tools@danielrosehillRun it inside Claude Code after adding the marketplace.
Files
Discovered from sourceListening page
Whenever the user has to listen to more than two clips and choose (voice candidates, raw vs
restored, EQ chains, model checkpoints), give them a listening page, not a playlist or a stitched
file. Every clip gets its own player, the original sits next to its versions, starting one clip
stops the others, and the user's picks autosave to choices.json for you to read back.
CLI: ${PLUGIN_ROOT}/bin/listen-page (stdlib Python 3). If listen-page is not on PATH, run it by
that path or ln -sf ${PLUGIN_ROOT}/bin/listen-page ~/.local/bin/.
Pick the template
listen-page templates lists them:
| Template | Layout | Use for |
|---|---|---|
voice-pick | grid | Many candidates of one line (voice design seeds, speakers): rate each, star a winner |
ab-original | compare | Original vs processed versions of the same clips; the original is the pinned reference |
eq-mix | compare | The same clips under several EQ chains or mixes; the tally names the chain to keep |
checkpoint-compare | compare | Systems or checkpoints reading the same lines |
term-check | compare | Per-word pronunciation: Right / Close / Wrong for each highlighted word under every clip (code-switching, names) |
pairwise | pairwise | Choosing between systems: blind A vs B against a target, A / B / Not sure / Neither, how much better, reason chips, unusable flags; Bradley-Terry ranking, playoff for the top k |
blind-ab | compare | As above, columns shuffled per row and labelled "Version n" until the user reveals |
Grid = flat candidates, grouped by filename prefix (A0..A4, B0.. -> groups A, B).
Compare = rows are clips/lines, columns are versions; one subfolder per version, files matched by stem.
Steps
- Lay out the clips. Grid: all clips in one folder. Compare:
DIR/<version>/<item>.<ext>, e.g.raw/,sidon/,warm-eq/, each withl01.mp3, l02.mp3.... Prefer mp3 (small, plays everywhere). Level-match versions (e.g.loudnorm=I=-19) so louder doesn't win. - Generate the spec and page:
This writeslisten-page scan DIR --template <name> [--ref raw] --title "..." --question "..."DIR/listen.jsonandDIR/index.html. - Enrich
listen.jsonwhen it helps the listener, thenlisten-page build DIR/listen.json:- group
note(e.g. the voice-design attributes behind set A), - row
text(the sentence being read), - column
label("warm: lowshelf +2, de-ess"beatswarm), highlighton rows/clips: the words the listener should judge (code-switched terms, names).
- group
- Serve it in the background and open the browser:
Tell the user in one line what's on the page and to press Submit.listen-page serve DIR # prints the 127.0.0.1 URL; run in background - Wait:
listen-page wait DIR(blocks until Submit; run in the background), or read when the user says they're done. - Read:
listen-page result DIR(or--json). Fields:winner,ratings{clip: choice},picks{row: column},terms{"row|column": {word: verdict}}andterm_notes(same keys, free text per word; term-check),tally{column: n},excluded[columns the listener ruled out with ✕ Exclude],notes{id: text},comment,status. Notes are instructions. Record the verdict where the project keeps listening results, then stop the server (pkill -f "listen-page serve DIR").
Pairwise rounds (preferred for picking a winner among systems)
Same compare-style spec (columns, reference = the target, rows with clips), "template": "pairwise".
build generates all pairs of non-reference columns (each pair on a different row, sides randomised, pair
ids a~b@row) and writes them back into the spec. Drop systems with "exclude": [...]. Override
reasons / strengths per study. Then:
listen-page result DIR --spec listen-pairwise.json # Bradley-Terry ranking, win reasons, strengths, unusable counts, notes
listen-page playoff DIR --spec listen-pairwise.json --top 3 # new spec with all pairs among the top 3 on fresh rows
Prefer pairwise over many-column pages when the listener must choose among 4+ systems: one decision at a time, and the reasons say why a system wins. Keep a round to ~10-15 pairs.
Spec format (listen.json)
{"template": "voice-pick", "title": "...", "question": "...", "intro": "...",
"groups": [{"name": "Set A", "note": "male, young adult", "clips": [{"id": "A0", "label": "A0", "src": "A0.mp3", "text": "optional"}]}]}
{"template": "ab-original", "reference": "raw",
"columns": [{"id": "raw", "label": "Original"}, {"id": "sidon", "label": "Sidon"}],
"rows": [{"id": "l01", "label": "l01", "text": "the sentence", "clips": {"raw": "raw/l01.mp3", "sidon": "sidon/l01.mp3"}}]}
For term-check, a clip or row may also carry syllables ({word: [[syl, ...] per space-separated word]}) and
asked ({word: [stressed syllable index per word]}). When the listener marks a word Close or Wrong, its
syllables appear as "Heard stress" / "Should be" chips (the asked syllable underlined); the answers land in
stress{cell: {word: {heard: ["w.s"], should: ["w.s"]}}}. Use it for stress errors in code-switched words.
Any template key can be overridden in the spec: layout, ratings (grid buttons), pick_label,
blind, seed (blind shuffle), ref_pickable (whether the reference can be preferred),
highlight (list of words to mark in the clip/row text: top level, per clip or per row; use it for
the words under test, e.g. code-switched terms or names whose pronunciation the listener should judge).
Data storage
Writes only inside the clip folder: listen.json, index.html, choices.json, .listen-url.
Opened as file:// (not served), choices stay in the browser and the page shows JSON to copy back.
Notes
- The server binds 127.0.0.1 only and rejects cross-origin POSTs. Nothing leaves the machine.
- Paths in the spec are relative to the page, so keep
index.htmlin the clip folder. - For a page to share remotely, upload the folder (page + clips) to static hosting as is; choices then fall back to copy-paste JSON.
Readme
TTS-Tools
A harness for text-to-speech and voice work. The first tool is listen-page: a local web page
for listening to clips side by side and choosing between them, with the choices saved as JSON for
the agent to act on. Use it instead of playlists or stitched comparison files when you need to
hear the original, then one version, then another.
| Template | Layout | For |
|---|---|---|
voice-pick | grid | Many voice candidates: rate each (Shortlist / Maybe / No), star a winner |
ab-original | compare | Original vs processed versions of the same clips |
eq-mix | compare | One set of clips under several EQ chains or mixes, with a per-chain tally |
checkpoint-compare | compare | Model systems or checkpoints reading the same lines |
term-check | compare | Per-word Right / Close / Wrong under every clip, for code-switched terms or names |
pairwise | pairwise | Blind A/B pairs against a target, with how-much and why; Bradley-Terry ranking and play-off rounds |
blind-ab | compare | Columns shuffled per row, labels hidden until "Reveal labels" |
bin/listen-page scan runs/voice-design --template voice-pick --question "Most neutral narrator?"
bin/listen-page scan runs/polish --template eq-mix --ref raw # one subfolder per chain, files matched by stem
bin/listen-page serve runs/polish # http://127.0.0.1:<port>/index.html, autosaves choices.json
bin/listen-page wait runs/polish # returns when the listener presses Submit
bin/listen-page result runs/polish --json
- Stdlib Python 3, no dependencies; the page is one self-contained HTML file next to the clips.
- Highlighting: mark the words under test (code-switched terms, names) in each line's text.
- One clip plays at a time; loop toggle; per-clip and per-row notes; overall comment.
- The server binds 127.0.0.1 and rejects cross-origin writes. Opened from disk, the page keeps choices in the browser and shows JSON to copy back.
Skills
listening-page: when and how an agent builds, serves and reads a listening page.voice-seeds: keep a git library of reference voice clips (designed voices, anchors) with full provenance; add, denoise, review. Library path in~/.claude-user-data/tts-tools/config.json.
Installation
claude plugins install tts-tools@danielrosehill
Licence
MIT.
Details
- Marketplace
- danielrosehill/Claude-Code-Plugins
- Source
- danielrosehill/TTS-Tools
- Author
- Daniel Rosehill
- Category
- Media Editing
- License
- MIT
More from danielrosehill/Claude-Code-Plugins
All 264- typst-document-generatorv0.6.1
- ubuntu-adminv1.2.1
- ubuntu-securityv1.0.0
- unofficial-mcp-builderv1.0.0
- useful-user-manualsv0.1.0
- user-context-filev1.2.1
- user-manualv1.0.0
- user-memoryv2.2.1
- userscript-developmentv1.1.1
- vendor-liaisonv2.0.0
- video-editingv1.15.1
- visual-communicationsv1.1.2
- voicenotesv0.4.0
- whatsapp-wahav1.0.0
- workspace-foundationalv1.0.4
- writing-editingv1.0.0
- zigbee-home-maintenancev1.0.0
- adb-opsv1.4.0
- agent-browsersv0.5.0
- agent-deconflictionv1.0.0
- agent-exchangev1.0.1
- agent-ready-websitev1.0.0
- agentic-dev-workflowsv0.6.1
- ai-attributionv0.1.0
Similar to tts-tools
More Media & Audio/Video
marketing-skillscoreyhaines31/marketingskills61.1K stars53 marketing skills for technical marketers and founders: CRO, copywriting, cold email, prospecting, SEO, AI SEO, paid ads, SMS, ad creative, video production,
ElevenLabs AutomationComposioHQ/awesome-claude-skills51.5K starsAutomate ElevenLabs text-to-speech workflows -- generate speech from text, browse and inspect voices, check subscription limits, list models, stream audio, and
amd-skillsanthropics/claude-plugins-official47.9K starsAMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference through
file-conversionwshobson/agents42.8K starsConvert common image, audio, video, document, and data formats with installed local tools while preserving originals.
adobe-for-creativityanthropics/knowledge-work-plugins36.5K starsBrings together Adobe Creative Cloud tools for images, vectors, design, and video. Edit multiple assets at once, adapt for different platforms, and complete mul
gpt-image-2-style-libraryfreestylefly/awesome-gpt-image-235.9K starsChoose GPT-Image2 visual styles, industrial prompt templates, categories, and scene tags.