feat: add comprehensive voice reference with 50+ voice catalog#8
Open
SecurityQQ wants to merge 1 commit intomainfrom
Open
feat: add comprehensive voice reference with 50+ voice catalog#8SecurityQQ wants to merge 1 commit intomainfrom
SecurityQQ wants to merge 1 commit intomainfrom
Conversation
- Add references/voices.md: full voice catalog (22 premade + 25 professional), voice_id passthrough docs, selection guide by use case, GET /v1/voices API with search/filter/pagination, POST /v1/voices/sync, VOICES global docs - Update models.md: replace hardcoded voice list with catalog link, add voice_id example in Speech usage - Update components.md: voice prop now documents voice_id support - Update gateway-api.md: expand POST /v1/speech with voice_id example, expand GET /v1/voices into full endpoint section with query params - Update SKILL.md: add voices.md to references table - Update recipes.md, templates.md: add voice_id comments in examples
📝 Walkthroughwalkthroughdocumentation updates across reference files to introduce elevenLabs voice_id support and voice catalog functionality. new comprehensive voices.md file documents voice selection methods, catalog details, and api endpoints. existing docs updated with voice_id examples and cross-references. changes
estimated code review effort🎯 2 (simple) | ⏱️ ~10 minutes possibly related prs
poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@varg-ai/references/voices.md`:
- Around line 31-87: The docs currently list 47 voices across the two tables
(the header rows "Name | voice_id | Gender | Age | Accent | Best for" and the
"Professional Voices" section), but elsewhere the PR claims "50+ curated
voices"; either update the promotional text to match the actual count (change
any "50+ curated voices" strings to "47 curated voices") or add the missing
voice entries to these tables so they total 50+ and ensure the tables and any
summary text (search for the literal "50+ curated voices") are consistent;
modify the entries in the two tables (including the Professional Voices block
and the main voices table) so the voice_ids and names align with the updated
count.
- Line 20: Update the documentation line that defines "An ElevenLabs voice_id"
to remove the hard-coded "20-char alphanumeric" constraint and instead state it
accepts any valid ElevenLabs voice_id (i.e., make the description for the
voice_id opaque and not length/format-specific); locate the phrase "**An
ElevenLabs voice_id**" / `voice_id` in voices.md and replace the restrictive
format text with wording like "any valid ElevenLabs voice_id" to avoid implying
an exact length or character set.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: a6647736-e84d-48ec-aaa5-12552c273959
📒 Files selected for processing (7)
varg-ai/SKILL.mdvarg-ai/references/components.mdvarg-ai/references/gateway-api.mdvarg-ai/references/models.mdvarg-ai/references/recipes.mdvarg-ai/references/templates.mdvarg-ai/references/voices.md
|
|
||
| The `voice` parameter accepts: | ||
| - **A friendly name** — `"adam"`, `"rachel"`, `"sarah"` etc. Resolved to a voice_id automatically. | ||
| - **An ElevenLabs voice_id** — any 20-char alphanumeric string like `"pNInz6obpgDQGcFmaJgB"`. Passed through directly. |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
what is the current official format/length guarantee (if any) for elevenlabs voice_id values in the voices api?
💡 Result:
ElevenLabs does not publish an official format or length guarantee for voice_id values. In the current Voices API reference, voice_id is specified only as a required string path parameter (“ID of the voice to be used”) and as a string field in responses—without regex/UUID constraints or min/max length. [1], [2]
In practice, the docs’ examples show IDs like 21m00Tcm4TlvDq8ikWAM (20 characters, mixed-case alphanumeric), but that appears to be an example rather than a contractual guarantee—so you should treat voice_id as an opaque string identifier. [1]
Sources: [1], [2]
voice_id format is too strictly defined
elevenlabs doesn't publish official format or length guarantees for voice_id values—they're opaque string identifiers. the doc's "20-char alphanumeric" claim is misleading since that's just what the examples happen to be. change to "any valid elevenlabs voice_id" without hard constraints. meow. 🐱
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@varg-ai/references/voices.md` at line 20, Update the documentation line that
defines "An ElevenLabs voice_id" to remove the hard-coded "20-char alphanumeric"
constraint and instead state it accepts any valid ElevenLabs voice_id (i.e.,
make the description for the voice_id opaque and not length/format-specific);
locate the phrase "**An ElevenLabs voice_id**" / `voice_id` in voices.md and
replace the restrictive format text with wording like "any valid ElevenLabs
voice_id" to avoid implying an exact length or character set.
Comment on lines
+31
to
+87
| | Name | voice_id | Gender | Age | Accent | Best for | | ||
| |------|----------|--------|-----|--------|----------| | ||
| | Adam | `pNInz6obpgDQGcFmaJgB` | male | middle_aged | american | social media, narration | | ||
| | Alice | `Xb7hH8MSUJpSbSDYk0k2` | female | middle_aged | british | educational, explainers | | ||
| | Bella | `hpp4J3VqNfWAUOO0d1Us` | female | middle_aged | american | educational, professional | | ||
| | Bill | `pqHfZKP75CvOlQylNhV4` | male | old | american | ads, authoritative | | ||
| | Brian | `nPczCjzI2devNBz1zQrb` | male | middle_aged | american | social media, comforting | | ||
| | Callum | `N2lVS1w4EtoT3dr4eOWO` | male | middle_aged | american | characters, animation | | ||
| | Charlie | `IKne3meq5aSn9XLyUdCD` | male | young | australian | conversational, energetic | | ||
| | Chris | `iP95p4xoKVk53GoZ742B` | male | middle_aged | american | conversational | | ||
| | Daniel | `onwK4e9ZLuTAKqWW03F9` | male | middle_aged | british | news, educational | | ||
| | Eric | `cjVigY5qzO86Huf0OWal` | male | middle_aged | american | conversational, trustworthy | | ||
| | George | `JBFqnCBsd6RMkjVDRZzb` | male | middle_aged | british | storytelling, narration | | ||
| | Harry | `SOYHLrjzK2X1ezoPC6cr` | male | young | american | characters, animation | | ||
| | Jessica | `cgSgspJ2msm6clMCkdW9` | female | young | american | conversational, bright | | ||
| | Laura | `FGY2WhTYpPnrIDTdsKH5` | female | young | american | social media, quirky | | ||
| | Liam | `TX3LPaxmHKxFdv7VOQHJ` | male | young | american | social media, energetic | | ||
| | Lily | `pFZP5JQG7iQjIQuC4Bku` | female | middle_aged | british | educational, velvety | | ||
| | Matilda | `XrExE9yKIg1WjnnlVkGX` | female | middle_aged | american | educational, professional | | ||
| | Rachel | `21m00Tcm4TlvDq8ikWAM` | female | young | american | default, general purpose | | ||
| | River | `SAz9YHcvj6GT2YYXdXww` | neutral | middle_aged | american | conversational, relaxed | | ||
| | Roger | `CwhRBWXzGAHq8TQ4Fs17` | male | middle_aged | american | conversational, casual | | ||
| | Sarah | `EXAVITQu4vr4xnSDxMaL` | female | young | american | entertainment, confident | | ||
| | Will | `bIHbv24MWmeRgasZH58o` | male | young | american | conversational, optimistic | | ||
|
|
||
| ### Professional Voices | ||
|
|
||
| Curated professional voices with distinctive characters. | ||
|
|
||
| | Name | voice_id | Gender | Age | Accent | Best for | | ||
| |------|----------|--------|-----|--------|----------| | ||
| | Adam (Brooding) | `IRHApOXLvnW57QJPQH2P` | male | middle_aged | american | characters, animation | | ||
| | Adeline | `5l5f8iK3YPeGga21rQIX` | female | middle_aged | american | narration, storytelling | | ||
| | Aja | `eVItLK1UvXctxuaRV2Oq` | female | young | american | villains, characters | | ||
| | Arabella | `aEO01A4wXwd1O8GPgGlF` | female | young | australian | conversational | | ||
| | Brittney (Meditation) | `pjcYQlDFKMbcOUp6F5GD` | female | young | american | meditation, ASMR | | ||
| | Brittney (Social) | `kPzsL2i3teMYv0FxEYQ6` | female | young | american | social media, fun | | ||
| | David (ASMR) | `UvFmc37lQcxsSts1KwSb` | male | middle_aged | american | ASMR, whisper | | ||
| | Declan Sage | `kqVT88a5QfII1HNAEPTJ` | male | middle_aged | american | narration, captivating | | ||
| | Edward | `goT3UYdM9bhm0n2lmKQx` | male | middle_aged | british | dark characters, sexy | | ||
| | El Abuelo Charlie | `Yb8JGzcZyW5YYzenhRCm` | male | old | latin american | Spanish narration | | ||
| | Ellen | `BIvP0GN1cAtSRTxNHnWS` | female | young | german | conversational (German) | | ||
| | Empress J | `MHPwHxLx0nmGIb5Jnbly` | female | old | american | narration, powerful | | ||
| | Hope | `tnSpp4vdxKPjI9w0GnoV` | female | young | american | social media, upbeat | | ||
| | Ivanna | `tQ4MEZFJOzsahSEEZtHK` | female | young | american | sensual, intimate | | ||
| | Jeanette | `RILOU7YmBhvwJGDGjNmP` | female | old | british | audiobooks, narration | | ||
| | Jerry B. | `NxGA8X3YhTrnf3TRQf6Q` | male | middle_aged | british | horror, thriller, villain | | ||
| | Juniper | `aMSt68OGf4xUZAnLpTU8` | female | middle_aged | american | conversational | | ||
| | Linda | `0mLOQqwA3kovxF1ID7z6` | female | old | canadian | gentle, storytime | | ||
| | Lindsey | `JAATlCsz6GCH2vUjFcLg` | female | middle_aged | american | professional, warm | | ||
| | Lulu Lollipop | `ocZQ262SsZb9RIxcQBOj` | female | young | american | kids content, bubbly | | ||
| | Natasha | `Atp5cNFg1Wj5gyKD7HWV` | female | middle_aged | american | meditation | | ||
| | Oxley | `2gPFXx8pN3Avh27Dw5Ma` | male | middle_aged | american | evil character | | ||
| | Sameno | `hMK7c1GPJmptCzI4bQIu` | female | young | standard | anime, soft voice | | ||
| | Serafina | `4tRn1lSkEn13EVTuqb0g` | female | young | american | flirty, characters | | ||
| | Torsten | `iCEMyUhOwgAy0egMANye` | male | young | - | narration, raspy | | ||
|
|
There was a problem hiding this comment.
catalog size messaging is inconsistent
these two tables currently list 47 curated voices, but other docs in this pr say “50+ curated voices”. please align the count claim or add the missing entries so users don’t get conflicting guidance.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@varg-ai/references/voices.md` around lines 31 - 87, The docs currently list
47 voices across the two tables (the header rows "Name | voice_id | Gender | Age
| Accent | Best for" and the "Professional Voices" section), but elsewhere the
PR claims "50+ curated voices"; either update the promotional text to match the
actual count (change any "50+ curated voices" strings to "47 curated voices") or
add the missing voice entries to these tables so they total 50+ and ensure the
tables and any summary text (search for the literal "50+ curated voices") are
consistent; modify the entries in the two tables (including the Professional
Voices block and the main voices table) so the voice_ids and names align with
the updated count.
SecurityQQ
added a commit
that referenced
this pull request
Mar 26, 2026
- Add 'API key hygiene' as Critical Rule #8: never write raw key values into bash commands, always use $VARG_API_KEY env var reference - Option A (existing key): instruct user to run export themselves instead of pasting key to the agent - Option B (OTP): capture verify-otp response into $VARG_AUTH variable, immediately export VARG_API_KEY from it via grep/cut - Save credentials: use $VARG_API_KEY variable reference instead of THE_KEY placeholder that agents substitute with the raw value - Stripe checkout: extract access_token into $VARG_ACCESS_TOKEN from the captured $VARG_AUTH response - Bump version to 2.0.4
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a dedicated voices.md reference and updates all existing skill files to document the new voice registry with voice_id passthrough support.
New:
references/voices.mdA complete voice reference covering:
GET /v1/voiceswith search, filter, pagination params and response format;POST /v1/voices/syncVOICESdata objectUpdated Files
SKILL.mdmodels.mdcomponents.mdvoiceprop descriptions on Speech() and TalkingHeadgateway-api.mdrecipes.mdtemplates.mdRelated PRs