New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deepgram Voice

by vellum-ai in vellum-ai/vellum-assistant

Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters

MITAuto-check passedMedia & Creative

Install Deepgram Voice

skills CLI
$ npx skills add vellum-ai/vellum-assistant --skill deepgram-voice -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vellum-ai/vellum-assistant deepgram-voice --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deepgram-voice .claude/skills/deepgram-voice && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deepgram-voice
GitHub stars
1.4k
Token cost
~2.6k tokens
SKILL.md length
1,037 words
Files
2 (incl. assets)
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters

  • Works in 2 steps: Switch to managed vellum… → Switch to BYO deepgram…
  • Tasks that involve Text to speech and voice
  • SKILL.md covers Overview, Getting to a Deepgram voice…, Choose a Voice and Deepgram API Key Setup, plus 3 more sections
  • Calls curl and python3; reaches api.deepgram.com

What it does

Deepgram Voice is an agent skill from vellum-ai/vellum-assistant. Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including assets. Compatibility notes: Designed for Vellum personal assistants

It sits in Media & Creative, covering Text to speech and voice. It works with Deepgram and ElevenLabs. The repository describes itself as: An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time. The licence is MIT.

When your agent uses it

  • Tasks that involve Text to speech and voice

Example prompts

  • “/deepgram-voice”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Designed for Vellum personal assistants

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Switch to managed vellum (voice_config_update setting="tts_provider" value="vellum") — no Deepgram key needed; requires a platform…
  2. Switch to BYO deepgram (voice_config_update setting="tts_provider" value="deepgram") — requires a Deepgram API key (setup below); usage…

What it can do on your machine

Read from SKILL.md and the folder at commit 33cc983. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.deepgram.com

    Also links to:

    • console.deepgram.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Vellum personal assistants

    From compatibility in the SKILL.md frontmatter.

Context cost

Deepgram Voice loads about 2.6k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 1,037 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vellum-ai/vellum-assistant at commit 33cc983, republished under its MIT licence (© vellum-ai). 1,037 words, ~2,596 tokens.

Download SKILL.mdSave it as .claude/skills/deepgram-voice/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
deepgram-voice
description
Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters
compatibility
Designed for Vellum personal assistants
metadata.icon
assets/icon.svg
metadata.emoji
🎤

Overview

Deepgram provides text-to-speech voices (the Aura model family) for both in-app TTS and phone calls. Change the voice with the voice_config_update tool — it writes the voice to whichever TTS provider is currently active and pushes to the macOS app via SSE in one call:

voice_config_update setting="tts_voice_id" value="<aura-model-id>"

The voice lives under the active provider, not always Deepgram. The config key depends on services.tts.provider: deepgram → services.tts.providers.deepgram.model, vellum (managed) → services.tts.providers.vellum.model, elevenlabs → services.tts.providers.elevenlabs.voiceId. The voice_config_update tool (and the assistant tts voice <id> CLI command) handle this routing for you. Do NOT assistant config set services.tts.providers.deepgram.model ... blindly — on a managed (vellum) assistant that field is ignored, so the write "succeeds" but the voice never changes. See Setting the voice for the CLI fallback.

The tables below apply when the active provider is deepgram (BYO key) or managed vellum. Managed assistants synthesize Deepgram voices through the platform — the platform bills per rate-carded model and rejects voices it does not offer (the write succeeds but the voice fails on the next turn), so stick to current Aura-2 voices there. With a BYO key (setup below), any Aura model id from the catalog works. Other BYO TTS providers (elevenlabs, xai, fish-audio, …) use their own voice identifiers — never write a Deepgram Aura model id to them; see Getting to a Deepgram voice from another provider.

Getting to a Deepgram voice from another provider

Check the active provider first: assistant config get services.tts.provider.

  • Already on managed vellum? No provider change needed. The managed platform supports both Deepgram and ElevenLabs voices — services.tts.providers.vellum.model accepts either an Aura model id or an ElevenLabs voice id, so switching between a Deepgram and an ElevenLabs voice is just another voice_config_update call.
  • On a BYO provider (e.g. elevenlabs) and the user wants a Deepgram voice? Two options — ask which they prefer. Switch with the voice_config_update tool, not raw assistant config set — the tool validates the switch (e.g. rejects vellum when no platform connection exists, which a raw config write would leave silently broken):
    1. Switch to managed vellum (voice_config_update setting="tts_provider" value="vellum") — no Deepgram key needed; requires a platform connection and bills managed credits. Bonus: they keep access to both the Deepgram and ElevenLabs catalogs.
    2. Switch to BYO deepgram (voice_config_update setting="tts_provider" value="deepgram") — requires a Deepgram API key (setup below); usage bills their Deepgram account directly.

After either switch, set the voice with voice_config_update as usual.

Choose a Voice

Pick a voice that matches your identity and the user's preferences. Offer to show the full list if they want to choose themselves. All voice ids follow the pattern aura-2-<name>-en.

Female voices
VoiceStyleModel ID
ThaliaClear, confident, energetic (American)aura-2-thalia-en
LunaFriendly, natural, engaging (American)aura-2-luna-en
AthenaCalm, smooth, professional (American)aura-2-athena-en
HeraWarm, smooth, professional (American)aura-2-hera-en
Male voices
VoiceStyleModel ID
ZeusDeep, trustworthy, smooth (American)aura-2-zeus-en
OrionApproachable, calm, polite (American)aura-2-orion-en
ArcasNatural, smooth, comfortable (American)aura-2-arcas-en
ApolloConfident, casual, comfortable (American)aura-2-apollo-en
DracoWarm, trustworthy, baritone (British)aura-2-draco-en
HyperionCaring, warm, empathetic (Australian)aura-2-hyperion-en

These are Aura-2 voices — Deepgram's current generation. First-generation ids (aura-asteria-en, aura-orion-en, … without the -2-) still work with a BYO key but sound noticeably flatter; prefer Aura-2 unless the user asks otherwise. aura-2-thalia-en is the managed platform's default voice.

Setting the voice

Preferred — the tool. It writes to the active provider's voice field and pushes to the macOS app via SSE (ttsVoiceId) in one call:

voice_config_update setting="tts_voice_id" value="<selected-model-id>"

CLI fallback (only if the voice_config_update tool is unavailable). Use assistant tts voice, which routes to the active provider's config key for you — do not hand-write assistant config set services.tts.providers.deepgram.model ...:

bash
assistant tts voice "<selected-model-id>"

Setting services.tts.providers.deepgram.model directly while the active provider is vellum (or any non-deepgram provider) is the #1 cause of "I changed the voice but it didn't change" — that field is ignored by the active provider, so the write reports success but nothing changes. If you must use config set, first check assistant config get services.tts.provider and write the matching key (vellum → services.tts.providers.vellum.model, deepgram → services.tts.providers.deepgram.model).

Verify it worked by reading back the key for the active provider, e.g. for a managed assistant:

bash
assistant config get services.tts.providers.vellum.model

The change hot-applies to the next voice turn (live voice and phone read the config fresh each turn).

Tell the user what voice you chose and why, but also offer to show all available voices so they can choose for themselves.

Show full SKILL.md (329 more words)Show less

Deepgram API Key Setup

When the active provider is vellum (managed), no key is needed — the platform handles Deepgram synthesis and billing. A key is only required when the provider is deepgram (BYO key), or for browsing the full catalog. Get one at https://console.deepgram.com (free credit available).

To collect the API key securely:

bash
assistant credentials prompt --service deepgram --field api_key --label "Deepgram API Key"

The same key is shared with Deepgram speech-to-text — storing it once covers both.

Advanced Voice Selection (with API key)

Users with a Deepgram API key can go beyond the curated list above — only when the active provider is deepgram (BYO key). On managed vellum, stay with the curated voices: the platform only accepts its rate-carded subset, and an unoffered id is persisted successfully but fails on the next spoken turn.

Check for an existing key
bash
assistant credentials inspect --service deepgram --field api_key --json
Browse the voice library

Deepgram's models endpoint returns the full TTS catalog, including each voice's characteristics and accent:

bash
curl -s "https://api.deepgram.com/v1/models" \
  -H "Authorization: Token $(assistant credentials reveal --service deepgram --field api_key)" \
  | python3 -c "import json,sys; [print(m['canonical_name'], '-', m['metadata']['accent'], '-', ', '.join(m['metadata']['tags'])) for m in json.load(sys.stdin)['tts'] if m['architecture']=='aura-2']"
Search for a specific style

Filter the same response by tag or accent (tags include descriptors like feminine, masculine, warm, casual, plus accents like British, Australian, Irish, and non-English-accented voices e.g. Spanish or Filipino):

bash
curl -s "https://api.deepgram.com/v1/models" \
  -H "Authorization: Token $(assistant credentials reveal --service deepgram --field api_key)" \
  | python3 -c "
import json, sys
query = 'warm british'.lower().split()
for m in json.load(sys.stdin)['tts']:
    if m['architecture'] != 'aura-2': continue
    hay = ' '.join([m['metadata']['accent'], *m['metadata']['tags']]).lower()
    if all(q in hay for q in query):
        print(m['canonical_name'], '-', m['metadata']['accent'], '-', ', '.join(m['metadata']['tags']))
"
Preview voices

Each voice in the models response includes a metadata.sample URL with an audio clip the user can listen to before deciding. To synthesize a custom preview line:

bash
curl -s -X POST "https://api.deepgram.com/v1/speak?model=<model-id>" \
  -H "Authorization: Token $(assistant credentials reveal --service deepgram --field api_key)" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hi! This is what I would sound like as your assistant."}' \
  -o scratch/voice-preview.mp3
Set the chosen voice

After the user picks a voice from the catalog:

voice_config_update setting="tts_voice_id" value="<selected-model-id>"

Voice Tuning

Deepgram Aura has no speed/stability/similarity parameters — expressiveness is baked into each voice, so if the sound isn't right, switch voices rather than hunting for a knob. The only tunable is the output format used for call/runtime playback when the active provider is deepgram:

bash
# Output audio format: mp3 (default), wav, or opus
assistant config set services.tts.providers.deepgram.format mp3

Voice Model Tuning

There is no separate model-id setting — the voice id is the model id, and the generation is part of it: aura-2-* ids use Aura-2, bare aura-*-en ids use first-generation Aura. To move a voice between generations, change the id itself, e.g. aura-asteria-en (Aura-1) → aura-2-asteria-en (Aura-2). Managed (vellum) assistants should always use Aura-2 ids — the platform only rate-cards current models.

© vellum-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (assets) in skills/deepgram-voice of vellum-ai/vellum-assistant.

  • SKILL.md
  • assets/icon.svg

Open the folder on GitHubat commit 33cc983

Compare with similar skills

Deepgram Voice next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deepgram Voice compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deepgram Voice this skillvellum-ai/vellum-assistant1.4k—~2.6kAutomated safety check: PassMIT
9Router Text to Speechdecolua/9router31k—~765Automated safety check: PassMIT
Keirouter Ttsmydisha/keirouter147—~599Automated safety check: PassMIT
Voice AI Developmentdavila7/claude-code-templates33k5 repos~2.1kAutomated safety check: PassMIT
Musictadaspetra/loop2962 repos~827Automated safety check: PassMIT
ElevenLabs Voiceover Generatordigitalsamba/claude-code-video-toolkit2.2k1 repos~2.7kAutomated safety check: NotesMIT

Similar skills

  • 9Router Text to Speech

    decolua/9router

    Turns text into spoken audio through a 9Router server, choosing among voices from OpenAI, ElevenLabs, Deepgram, Edge TTS and other providers.

    31k GitHub stars~765 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

  • Keirouter Tts

    mydisha/keirouter

    Text-to-speech via KeiRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Inworld voices.

    147 GitHub stars~599 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Voice AI Development

    davila7/claude-code-templates

    Expert in building voice AI applications - from real-time voice agents to voice-enabled apps.

    33k GitHub starsUsed in 5 repos~2.1k tokens
    Media & CreativeAuto-check passed

  • Music

    tadaspetra/loop

    Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~827 tokens
    Media & CreativeAuto-check passed

  • ElevenLabs Voiceover Generator

    digitalsamba/claude-code-video-toolkit

    Generates narration, sound effects and cloned voices through the ElevenLabs API, with model and setting choices tuned to the content's style.

    2.2k GitHub starsUsed in 1 repo~2.7k tokens
    Media & CreativeAuto-check: notes

  • Sound Effects

    tadaspetra/loop

    Generate sound effects from text descriptions using ElevenLabs.

    296 GitHub starsUsed in 2 repos~1.1k tokens
    Media & CreativeAuto-check passed

More from vellum-ai/vellum-assistant

All 108 skills in this repo

  • Vellum GitHub App Setup

    vellum-ai/vellum-assistant

    Create and configure a GitHub App so the assistant can push commits, open PRs, and comment under its own bot identity.

    1.4k GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed

  • Discord App Setup

    vellum-ai/vellum-assistant

    Connect a Discord bot to the assistant via the Discord Gateway with guided application creation and intent configuration

    1.4k GitHub stars~4.2k tokensUpdated 2 days ago
    Auto-check passed

  • Sentry App Setup

    vellum-ai/vellum-assistant

    Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity

    1.4k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

  • Memory Corpus Ingest

    vellum-ai/vellum-assistant

    Ingest a large dataset into memory as a skimmed map. An agent skill from vellum-ai/vellum-assistant.

    1.4k GitHub stars~3k tokensUpdated 2 days ago
    Auto-check: notes

  • Plugin Builder

    vellum-ai/vellum-assistant

    A skill your agent uses when the user wants to build, scaffold, ship, or edit a Vellum plugin that bundles multiple surfaces (hooks, tools, skills, and more) into one installable package.

    1.4k GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed

  • Slack App Setup

    vellum-ai/vellum-assistant

    Connect a Slack app to the Vellum Assistant via Socket Mode.

    1.4k GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check: warnings

Works with

Categories

Questions about Deepgram Voice

What does Deepgram Voice do?

Select and tune a Deepgram TTS voice - curated voice list, full Aura voice catalog via API key, and tuning parameters. Deepgram Voice is an agent skill from vellum-ai/vellum-assistant.

When should I use Deepgram Voice?

Deepgram Voice fits situations like: tasks that involve Text to speech and voice.

How do I install Deepgram Voice in Claude Code?

Run `npx skills add vellum-ai/vellum-assistant --skill deepgram-voice -a claude-code`. Or copy the skill folder (skills/deepgram-voice in vellum-ai/vellum-assistant) into .claude/skills/deepgram-voice in your project. Claude Code loads it when a task matches its description.

How do I install Deepgram Voice in Codex?

Run `npx skills add vellum-ai/vellum-assistant --skill deepgram-voice -a codex`. Or copy the skill folder (skills/deepgram-voice in vellum-ai/vellum-assistant) into .agents/skills/deepgram-voice in your project. Codex loads it when a task matches its description.

Can I use Deepgram Voice in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vellum-ai/vellum-assistant --skill deepgram-voice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepgram-voice, .gemini/skills/deepgram-voice, .github/skills/deepgram-voice and .opencode/skills/deepgram-voice in your project.

What does Deepgram Voice need to run?

Going by SKILL.md and its folder, Deepgram Voice needs the command-line tools its instructions call (curl and python3). Our summary lists: Python 3. Compatibility (from SKILL.md): Designed for Vellum personal assistants.

Does Deepgram Voice access the network?

SKILL.md names 2 domains. In commands or code: api.deepgram.com; the agent is likely to contact it when it follows the instructions. As links in the text: console.deepgram.com. This is read from the text; nothing was executed.

Is Deepgram Voice safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deepgram Voice use?

Deepgram Voice is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepgram Voice use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deepgram Voice?

Skills that share tags, products or a category with Deepgram Voice: 9Router Text to Speech (decolua/9router, 31k stars), Keirouter Tts (mydisha/keirouter, 147 stars), Voice AI Development (davila7/claude-code-templates, 33k stars) and Music (tadaspetra/loop, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepgram Voice?

vellum-ai (a GitHub organization) maintains it in vellum-ai/vellum-assistant, which has 1,408 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on October 9, 2026.

Source: vellum-ai/vellum-assistant on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.