惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
罗磊的独立博客
M
MIT News - Artificial intelligence
G
Google Developers Blog
V
V2EX
D
Docker
博客园_首页
The Cloudflare Blog
人人都是产品经理
人人都是产品经理
Y
Y Combinator Blog
WordPress大学
WordPress大学
T
Tailwind CSS Blog
博客园 - 司徒正美
J
Java Code Geeks
L
LangChain Blog
博客园 - 三生石上(FineUI控件)
B
Blog RSS Feed
博客园 - 【当耐特】
小众软件
小众软件
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
P
Proofpoint News Feed
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - Franky

Simon Willison's Weblog

Release: datasette 1.0a29 Thoughts on GitLab’s workforce reduction A quote from James Shore Your AI Use Is Breaking My Brain TIL: Using LLM in the shebang line of a script Learning on the Shop floor A quote from New York Times Editors’ Note A quote from Andrew Quinn A quote from Luke Curley Release: llm-gemini 0.31 Tool: Big Words Behind the Scenes Hardening Firefox with Claude Mythos Preview Notes on the xAI/Anthropic data center deal Tool: GitHub Repo Stats Live blog: Code w/ Claude 2026 Vibe coding and agentic engineering are getting closer than I’d like Release: datasette-referrer-policy 0.1 Release: datasette-llm 0.1a7 Release: llm-echo 0.5a0 Granite 4.1 3B SVG Pelican Gallery A quote from Andy Masley April 2026 newsletter Research: TRE Python binding — ReDoS robustness demo Tool: Redis Array Playground A quote from Anthropic Sightings iNaturalist Sightings Codex CLI 0.128.0 adds /goal Our evaluation of OpenAI's GPT-5.5 cyber capabilities Quoting Andrew Kelley
Gemini 3.1 Flash TTS
2026-04-16 · via Simon Willison's Weblog

15th April 2026 - Link Blog

Gemini 3.1 Flash TTS. Google released Gemini 3.1 Flash TTS today, a new text-to-speech model that can be directed using prompts.

It's presented via the standard Gemini API using gemini-3.1-flash-tts-preview as the model ID, but can only output audio files.

The prompting guide is surprising, to say the least. Here's their example prompt to generate just a few short sentences of audio:

# AUDIO PROFILE: Jaz R.
## "The Morning Hype"

## THE SCENE: The London Studio
It is 10:00 PM in a glass-walled studio overlooking the moonlit London skyline, but inside, it is blindingly bright. The red "ON AIR" tally light is blazing. Jaz is standing up, not sitting, bouncing on the balls of their heels to the rhythm of a thumping backing track. Their hands fly across the faders on a massive mixing desk. It is a chaotic, caffeine-fueled cockpit designed to wake up an entire nation.

### DIRECTOR'S NOTES
Style:
* The "Vocal Smile": You must hear the grin in the audio. The soft palate is always raised to keep the tone bright, sunny, and explicitly inviting.
* Dynamics: High projection without shouting. Punchy consonants and elongated vowels on excitement words (e.g., "Beauuutiful morning").

Pace: Speaks at an energetic pace, keeping up with the fast music.  Speaks with A "bouncing" cadence. High-speed delivery with fluid transitions — no dead air, no gaps.

Accent: Jaz is from Brixton, London

### SAMPLE CONTEXT
Jaz is the industry standard for Top 40 radio, high-octane event promos, or any script that requires a charismatic Estuary accent and 11/10 infectious energy.

#### TRANSCRIPT
[excitedly] Yes, massive vibes in the studio! You are locked in and it is absolutely popping off in London right now. If you're stuck on the tube, or just sat there pretending to work... stop it. Seriously, I see you.
[shouting] Turn this up! We've got the project roadmap landing in three, two... let's go!

Here's what I got using that example prompt:

Then I modified it to say "Jaz is from Newcastle" and "... requires a charismatic Newcastle accent" and got this result:

Here's Exeter, Devon for good measure:

I had Gemini 3.1 Pro vibe code this UI for trying it out:

Screenshot of a "Gemini 3.1 Flash TTS" web application interface. At the top is an "API Key" field with a masked password. Below is a "TTS Mode" section with a dropdown set to "Multi-Speaker (Conversation)". "Speaker 1 Name" is set to "Joe" with "Speaker 1 Voice" set to "Puck (Upbeat)". "Speaker 2 Name" is set to "Jane" with "Speaker 2 Voice" set to "Kore (Firm)". Under "Script / Prompt" is a tip reading "Tip: Format your text as a script using the Exact Speaker Names defined above." The script text area contains "TTS the following conversation between Joe and Jane:\n\nJoe: How's it going today Jane?\nJane: [yawn] Not too bad, how about you?" A blue "Generate Audio" button is below. At the bottom is a "Success!" message with an audio player showing 00:00 / 00:06 and a "Download WAV" link.