Voice AI Engine Development
aiskillstore/marketplace
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support
Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models.
Install Speech Build
$ npx skills add cnemri/google-genai-skills --skill speech-build -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cnemri/google-genai-skills speech-build --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/speech-build .claude/skills/speech-build && rm -rf skills-srcUse ~/.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/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .claude/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-buildType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cnemri/google-genai-skills --skill speech-build -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cnemri/google-genai-skills speech-build --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/speech-build .agents/skills/speech-build && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .agents/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cnemri/google-genai-skills --skill speech-build -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cnemri/google-genai-skills speech-build --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/speech-build .cursor/skills/speech-build && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .cursor/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cnemri/google-genai-skills.git --path skills/speech-build--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cnemri/google-genai-skills --skill speech-build -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cnemri/google-genai-skills speech-build --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/speech-build .gemini/skills/speech-build && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .gemini/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cnemri/google-genai-skills speech-buildInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cnemri/google-genai-skills --skill speech-build -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/speech-build .github/skills/speech-build && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .github/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cnemri/google-genai-skills --skill speech-build -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cnemri/google-genai-skills speech-build --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cnemri/google-genai-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/speech-build .opencode/skills/speech-build && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "speech-build" agent skill from https://github.com/cnemri/google-genai-skills/tree/main/skills/speech-build into .opencode/skills/speech-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "speech-build", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
speech-build- GitHub stars
- 127
- Token cost
- ~430 tokens
- SKILL.md length
- 78 words
- Files
- 6 (incl. references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models.
- Works in 2 steps: Generate Speech (Gemini-TTS) → Transcribe Audio (Chirp 3)
- Tasks that involve Transcription
- SKILL.md covers Quick Start Setup, Reference Materials and Common Workflows
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Speech Build is an agent skill from cnemri/google-genai-skills. Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models. Supports Text-to-Speech (Single/Multi-speaker), Instant Custom Voice, and Speech-to-Text (Transcription/Diarization).
Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/prompting.md`, `references/source_code.md` and `references/stt.md`).
It sits in Media & Creative, covering Transcription, Text to speech and voice and Speech recognition and synthesis. The licence is MIT.
When your agent uses it
- Tasks that involve Transcription
- Tasks that involve Text to speech and voice
- Tasks that involve Speech recognition and synthesis
Example prompts
- “/speech-build”
Requirements
- Python 3
Workflow steps
2 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 7277476. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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.
Context cost
Speech Build loads about 430 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 78 words of instructions outside code blocks.
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 cnemri/google-genai-skills at commit 7277476, republished under its MIT licence (© cnemri). 78 words, ~430 tokens.
Download SKILL.mdSave it as
.claude/skills/speech-build/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- speech-build
- description
- Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models. Supports Text-to-Speech (Single/Multi-speaker), Instant Custom Voice, and Speech-to-Text (Transcription/Diarization).
Speech Skill (TTS & STT)
Use this skill to implement audio generation and transcription workflows using the google-genai and google-cloud-speech SDKs.
Quick Start Setup
from google import genai
from google.genai import types
# For STT: from google.cloud import speech_v2
client = genai.Client()Reference Materials
- Text-to-Speech (TTS): Gemini-TTS, Chirp 3 HD, Instant Custom Voice.
- Speech-to-Text (STT): Chirp 3 Transcription, Diarization, Streaming.
- Voices & Locales: Available voices (
Aoede,Puck...) and languages. - Prompting Guide: How to control style, accent, and pacing in Gemini-TTS.
- Source Code: Deep inspection of SDK internals.
Common Workflows
1. Generate Speech (Gemini-TTS)
response = client.models.generate_content(
model="gemini-2.5-flash-preview-tts",
contents="Hello, world!",
config=types.GenerateContentConfig(
response_modalities=["AUDIO"],
speech_config=types.SpeechConfig(
voice_config=types.VoiceConfig(
prebuilt_voice_config=types.PrebuiltVoiceConfig(voice_name='Kore')
)
)
)
)2. Transcribe Audio (Chirp 3)
# Requires google-cloud-speech
from google.cloud import speech_v2
# ... (See stt.md for full setup)
response = speech_client.recognize(...)© cnemri, 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 5 other files (references) in skills/speech-build of cnemri/google-genai-skills.
- SKILL.md
- references/prompting.md
- references/source_code.md
- references/stt.md
- references/tts.md
- references/voices.md
Open the folder on GitHubat commit 7277476
Compare with similar skills
Speech Build 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Speech Build this skillcnemri/google-genai-skills | 127 | — | ~430 | Automated safety check: Pass | MIT | |
| Voice AI Engine Developmentaiskillstore/marketplace | 430 | 5 repos | ~5.7k | Automated safety check: Pass | None | |
| Stepfun Asrdaymade/claude-code-skills | 1.4k | — | ~3k | Automated safety check: Pass | MIT | |
| DeepgramAnil-matcha/awesome-muse-connectors | 1.3k | — | ~857 | Automated safety check: Pass | MIT | |
| Groq Core Workflow Bjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| AudiopodLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.5k | Automated safety check: Pass | MIT |
Similar skills
Stepfun Asr
daymade/claude-code-skills
Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking.
Deepgram
Anil-matcha/awesome-muse-connectors
Deepgram speech AI: transcribe audio to text and synthesize speech (TTS).
Groq Core Workflow B
jeremylongshore/tons-of-skills-marketplace
A skill your agent uses when you need Groq's non-chat endpoints — transcribing or translating audio with Whisper, understanding images with Llama 4 vision, generating speech (TTS), or benchmarking…
Audiopod
LeoYeAI/openclaw-master-skills
Use AudioPod AI's API for audio processing tasks including AI music generation (text-to-music, text-to-rap, instrumentals, samples, vocals), stem separation, text-to-speech, noise reduction…
Fal Audio
aiskillstore/marketplace
Text-to-speech and speech-to-text using fal.ai audio models. An agent skill from aiskillstore/marketplace.
More from cnemri/google-genai-skills
All 10 skills in this repoDeep Research
cnemri/google-genai-skills
Perform autonomous, multi-step research using the Gemini Deep Research Agent (Interactions API).
Speech Use
cnemri/google-genai-skills
Generate (TTS), Transcribe (STT), and Clone voices using Google's GenAI and Cloud Speech SDKs.
Veo Use
cnemri/google-genai-skills
Create and edit videos using Google's Veo 2 and Veo 3 models.
Google Developer Knowledge
cnemri/google-genai-skills
Search and retrieve Google's developer documentation using the Developer Knowledge API.
Nano Banana Use
cnemri/google-genai-skills
Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts.
Google Adk Python
cnemri/google-genai-skills
Expert guidance on the Google Agent Development Kit (ADK) for Python.
Related
Categories
Questions about Speech Build
What does Speech Build do?
Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models. Speech Build is an agent skill from cnemri/google-genai-skills. Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models.
When should I use Speech Build?
Speech Build fits situations like: tasks that involve Transcription; tasks that involve Text to speech and voice; tasks that involve Speech recognition and synthesis.
How do I install Speech Build in Claude Code?
Run `npx skills add cnemri/google-genai-skills --skill speech-build -a claude-code`. Or copy the skill folder (skills/speech-build in cnemri/google-genai-skills) into .claude/skills/speech-build in your project. Claude Code loads it when a task matches its description.
How do I install Speech Build in Codex?
Run `npx skills add cnemri/google-genai-skills --skill speech-build -a codex`. Or copy the skill folder (skills/speech-build in cnemri/google-genai-skills) into .agents/skills/speech-build in your project. Codex loads it when a task matches its description.
Can I use Speech Build 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 cnemri/google-genai-skills --skill speech-build -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speech-build, .gemini/skills/speech-build, .github/skills/speech-build and .opencode/skills/speech-build in your project.
What does Speech Build need to run?
SKILL.md names no scripts, command-line tools or credentials: Speech Build is instructions for the agent only. Our summary lists: Python 3.
Does Speech Build access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Speech Build 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 Speech Build use?
Speech Build 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 Speech Build use?
About 430 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Speech Build?
Skills that share tags, products or a category with Speech Build: Voice AI Engine Development (aiskillstore/marketplace, 430 stars), Stepfun Asr (daymade/claude-code-skills, 1.4k stars), Deepgram (Anil-matcha/awesome-muse-connectors, 1.3k stars) and Groq Core Workflow B (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Speech Build?
cnemri (a GitHub user) maintains it in cnemri/google-genai-skills, which has 127 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on February 6, 2026.
Source: cnemri/google-genai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.