skills.rest
Pixazo-AI
Pixazo-AIOFFICIAL
Explore all skills by this author →
Website𝕏@pixazoaiGitHub

gemini-voice

Generates speech from text and transcribes audio via the Gemini Voice API on Pixazo.

Updated May 2, 2026
Search Tags:#text-to-speech#transcription#audio generation#speech-to-text#voice synthesis#pixazo api#gemini voice
One-click install
npx skills add https://github.com/Pixazo-AI/skills --skill gemini-voice-pixazo-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-voice
Source: https://github.com/Pixazo-AI/skills/tree/main/skills/gemini-voice
Command: npx skills add https://github.com/Pixazo-AI/skills --skill gemini-voice-pixazo-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It lets an AI agent convert text into natural-sounding speech and transcribe recorded audio into text through Google's Gemini voice models, without the user needing to learn the underlying API details. ## Core Features & Use Cases - Text-to-Speech: Gemini 3.1 Flash TTS turns text into speech with 30 voices, natural-language delivery control, and two-speaker dialogue. - Speech-to-Text: Gemini 3.5 Transcribe converts recorded speech into text with speaker labels and word-level timestamps across 85+ locales. - Guided API Key Setup: Walks the agent through acquiring and saving a Pixazo API key once, then reuses it for all future calls. - Use Case: Ask your agent to read a blog post aloud as an MP3, or transcribe a recorded meeting with speaker labels and timestamps. ## Quick Start Ask your agent to convert this paragraph into spoken audio using Gemini Voice and give me the audio file URL.

Frequently Asked Questions about gemini-voice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech with the Gemini Voice API?▼

Send a POST request to the Pixazo gateway endpoint for gemini-3-1-flash-tts with your text and API key in the Ocp-Apim-Subscription-Key header. The response is synchronous and returns a JSON object containing the generated audio URL.

How do I transcribe audio to text with speaker labels?▼

Use the Gemini 3.5 Transcribe operation by posting your audio file URL to the speech-to-text endpoint. It returns text with speaker labels and word-level timestamps across more than 85 locales.

Where do I get a Pixazo API key for Gemini Voice?▼

Sign in at https://api-console.pixazo.ai/api_keys, click Create new key, and copy it. The skill saves it to ~/.pixazo/api-key so you only provide it once.

Does Gemini Voice text-to-speech require polling for results?▼

No, text-to-speech via this API is synchronous. The response immediately returns JSON containing the audio URL, with no polling loop required.

Why am I getting a 401 or 402 error from the Pixazo API?▼

A 401 means your API key is missing or invalid, so generate a fresh one at the Pixazo console. A 402 means your account is out of credits and needs a top-up at the Pixazo dashboard.

Related Skills

Explore More Content & Communication Skills→
Kastalien-ResearchKastalien-Research

summarize

Summarize or extract text from URLs, podcasts, and local files via CLI.

Official
Intermediate
taracodlabstaracodlabs
799

youtube-content

Extract transcripts, download audio and video, and retrieve metadata from YouTube videos.

Official
Basic
gyalamanch001agyalamanch001a

elevenlabs

Generate voiceovers, sound effects, and music from natural-language prompts via the ElevenLabs API.

Community
Advanced
JosiahSiegelJosiahSiegel
51

fal-audio

Transcribe audio, translate speech, synthesize voices, and clone voices.

Community
Advanced