What makes Google Gemini TTS notable?

974 downloads. Trust evidence available

How should Google Gemini TTS be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Google Gemini TTS

Generate spoken audio from text using Google's Gemini TTS models (default is Gemini 3.1 Flash TTS Preview, with fallback to Gemini 2.5 Flash/Pro preview TTS)... Skill: Google Gemini TTS Owner: shubhamsaboo Summary: Generate spoken audio from text using Google's Gemini TTS models (default is Gemini 3.1 Flash TTS Preview, with fallback to Gemini 2.5 Flash/Pro preview TTS)... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-04-16T00:04:27.800Z | user Rewrite Style control docs to match Gemini 3.1 Flash TTS prompting guide: distinguish inline audio tags from structured AUDIO PR

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

974

Updated

Oct 11, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 974 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 974 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.3release · observed Apr 16, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.3release
Rewrite Style control docs to match Gemini 3.1 Flash TTS prompting guide: distinguish inline audio tags from structured AUDIO PROFILE/SCENE/DIRECTOR'S NOTES/TRANSCRIPT blocks, list real tag examples (emotion, pace, non-verbal, character), drop old preamble-only bullets.
Observed Apr 16, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s176jey2ys9ggehnmve29zyq3x83gqtj:google-gemini-tts

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-shubhamsaboo-google-gemini-tts/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

42,692 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: google-gemini-tts
description: "Generate spoken audio from text using Google's Gemini TTS models (default is Gemini 3.1 Flash TTS Preview, with fallback to Gemini 2.5 Flash/Pro preview TTS). Use when an agent needs to convert text to speech, produce voice replies, narrate briefings or newsletters, create podcast-style two-speaker conversations, generate audio with expressive style control (whispers, pauses, accents, emotion), or output WAV files for voice-enabled workflows. Supports 30 prebuilt voices, 70+ languages, single and multi-speaker modes, and natural-language style prompts. Requires a GEMINI_API_KEY from Google AI Studio (the script also accepts GOOGLE_API_KEY as an alternative name for the same key)."
version: 1.0.3
author: Shubham Saboo
compatibility: Requires curl, jq, base64, ffmpeg, and a GEMINI_API_KEY from Google AI Studio. Preview model names may change as Google promotes them to GA.
metadata:
  openclaw:
    emoji: "🔊"
    homepage: https://ai.google.dev/gemini-api/docs/speech-generation
    requires:
      env:
        - GEMINI_API_KEY
      bins:
        - curl
        - jq
        - base64
        - ffmpeg
    primaryEnv: GEMINI_API_KEY
---

# Gemini TTS

Generate speech audio from text using Gemini TTS models. The default is Gemini 3.1 Flash TTS Preview, and the script still supports Gemini 2.5 preview TTS models when you pass `-m`.

## What this skill does

- Single-speaker text to speech
- Two-speaker podcast-style audio
- Style control with natural language prompts
- WAV output that can be sent directly in chat or used in apps

## Files

- `scripts/gemini_tts.sh`: CLI wrapper around the Gemini REST API

## Quick start

```bash
# Show all options
scripts/gemini_tts.sh --help

# Single speaker, default voice (Kore)
scripts/gemini_tts.sh "Hello, welcome to the show!"

# Pick a voice
scripts/gemini_tts.sh -v Puck "This is Puck speaking."

# With style control
scripts/gemini_tts.sh -s "Say in a warm, calm tone:" "Take a deep breath."

# Save to a specific file
scripts/gemini_tts.sh -o /tmp/greeting.wav "Hey there!"

# Multi-speaker conversation
scripts/gemini_tts.sh --multi "Host:Kore,Guest:Puck" \
  "Host: Welcome to the podcast! Guest: Thanks for having me."
```

The script prints the output WAV file path.

## Models

| Model | Best for |
|---|---|
| `gemini-3.1-flash-tts-preview` (default) | Best default now: low-latency, natural output, expressive narration |
| `gemini-2.5-flash-preview-tts` | Backward-compatible fast preview model |
| `gemini-2.5-pro-preview-tts` | Long-form narration and higher-end creative work |

Current note: Gemini 3.1 Flash TTS Preview is live and should be the default path for this skill. Gemini 2.5 preview TTS models remain useful as compatibility fallbacks.

> **Preview model note:** `gemini-3.1-flash-tts-preview` is a preview model. If Google renames or retires it, pass `-m gemini-2.5-flash-preview-tts` as a fallback, or check the [current model list](https://ai.google.dev/gemini-api

README.md

# gemini-tts

ClawHub-ready packaging for a Gemini text-to-speech skill.

Default target: Gemini 3.1 Flash TTS Preview.
Backward compatibility: Gemini 2.5 Flash Preview TTS and Gemini 2.5 Pro Preview TTS still work when passed with `-m`.

## What is in the bundle

- `SKILL.md`: publishable skill definition
- `scripts/gemini_tts.sh`: runnable shell wrapper for the Gemini REST API
- `.clawhubignore`: excludes generated artifacts from the bundle

## Why the new default matters

Gemini 3.1 Flash TTS Preview is the right default now because it combines:

- low-latency speech generation
- stronger naturalness
- expressive audio tags
- multilingual output
- single-speaker and two-speaker generation in one simple workflow

This makes the skill more than a plain narrator. It is good for agents that need controllable voice output, not just generic TTS.

## Prompting nuance

- audio tags like `[short pause]` and `[whisper]` work best inside a structured transcript or a clear instruction block
- a bare tag-heavy prompt without enough framing can return no audio
- practical takeaway: wrap tags in a real narration prompt, not just a pile of modifiers

## Tested prompt patterns that worked

Single speaker:

```text
Say in a spooky voice:
"By the pricking of my thumbs... [short pause]
[whisper] Something wicked this way comes"
```

Multi-speaker:

```text
Make Speaker1 sound tired and bored, and Speaker2 sound excited and happy:

Speaker1: So... [yawn] what's on the agenda today?
Speaker2: You're never going to guess!
```

## What agents can do with this

This model is especially useful when agents need to deliver output with intent.

Examples:

- Voice replies in chat: an agent can answer with a short spoken memo instead of plain text
- Daily briefings: a research agent can turn its morning findings into a narrated update
- Newsletter voice preview: a content agent can turn a written summary into a quick audio rundown
- Social content drafts: a marketing agent can generate spoken hooks, trailers, or teaser clips
- Podcast-style synthesis: two-agent conversations can become clean host and guest audio
- Demo agents: product agents can narrate walkthroughs, onboarding, or feature explanations
- Emotional delivery: agents can add pauses, whispers, excitement, boredom, or emphasis where it helps the message land

The main unlock is controllability. You are not just picking a voice. You are giving the agent delivery instructions.

## Usage examples

Default model:

```bash
scripts/gemini_tts.sh "Hello, welcome to the show!"
```

Pick a voice:

```bash
scripts/gemini_tts.sh -v Puck "This is Puck speaking."
```

Add style guidance:

```bash
scripts/gemini_tts.sh -s "Say in a warm, calm tone:" "Take a deep breath."
```

Use explicit audio tags in the transcript:

```bash
scripts/gemini_tts.sh -o /tmp/tagged.wav 'Say in a spooky voice:
"By the pricking of my thumbs... [short pause]
[whisper] Something wicked this way comes"'
```

Two-speaker audio:

```bash
scripts/gemin

_meta.json

{
  "ownerId": "kn7fhx3kpfzzdvb7hg46n42ea5831wxb",
  "slug": "google-gemini-tts",
  "version": "1.0.3",
  "publishedAt": 1776297867800
}

skill-card.md

## Description:

Generate spoken audio from text using Google's Gemini TTS models (default is Gemini 3.1 Flash TTS Preview, with fallback to Gemini 2.5 Flash/Pro preview TTS).

This skill is ready for commercial/non-commercial use.

## Publisher:

[shubhamsaboo](https://clawhub.ai/user/shubhamsaboo)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this skill to turn generated text into WAV speech for voice replies, briefings, narration, podcast-style two-speaker conversations, and style-controlled spoken output.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill sends user-provided text, style prompts, and related request data to Google's Gemini API.

Mitigation: Use it only for data your policy permits sending to Gemini, and avoid secrets, regulated data, or private documents unless approved.

Risk: Gemini API usage may consume quota or incur billing, especially when preview models are selected.

Mitigation: Monitor Google API quota and billing for the API key used by the agent.

Risk: Preview model names may change or be retired.

Mitigation: Check the current Gemini model list and use the documented fallback model option when needed.

## Reference(s):

- [Gemini speech generation documentation](https://ai.google.dev/gemini-api/docs/speech-generation)
- [Gemini model list](https://ai.google.dev/gemini-api/docs/models)
- [Google AI Studio API key setup](https://aistudio.google.com/apikey)
- [ClawHub skill page](https://clawhub.ai/shubhamsaboo/skills/google-gemini-tts)

## Skill Output:

**Output Type(s):** [Shell commands, Configuration, Audio files, Guidance]

**Output Format:** [Markdown guidance with shell commands; the runtime script writes a local WAV file path.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces 24 kHz mono, 16-bit PCM WAV output after converting Gemini audio response data with ffmpeg.]

## Skill Version(s):

1.0.3 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular