Product Update

What's New in eidosSpeech v2.1: Multi-Voice Scripts, Subtitles & Voice Emotions

We've shipped 9 game-changing features that transform how you create voice content. From multi-speaker dialogs to automatic subtitles, v2.1 is our biggest update yet.

eidosSpeech v2.1 multi-voice script interface

After months of development and feedback from our community, we're excited to announce eidosSpeech v2.1 — our most ambitious update yet. This release introduces features that content creators, developers, and businesses have been requesting since day one.

Let's dive into what's new.

🎭 Feature #1: Multi-Voice Script Mode

The most requested feature is finally here: multi-voice dialog scripts. Create conversations with multiple speakers, each with their own unique voice.

What Is Multi-Voice Script Mode?

Multi-voice script mode allows you to write dialog in a simple format and assign different AI voices to each speaker. Perfect for:

How It Works

Write your script in a simple format:

[John]: Hello, how are you today?
[Mary]: I'm doing great, thanks for asking!
[John]: That's wonderful to hear.
[Mary]: How about you?

Then assign voices to each speaker:

eidosSpeech automatically generates each line with the correct voice and merges them into a single MP3 file with customizable pauses between lines.

API Example

curl -X POST https://eidosspeech.xyz/api/v1/tts/script \
  -H "X-API-Key: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "[John]: Hello!\\n[Mary]: Hi there!",
    "voice_map": {
      "John": "en-US-GuyNeural",
      "Mary": "en-US-JennyNeural"
    },
    "pause_ms": 500
  }' \
  --output dialog.mp3

Web UI

We've added a dedicated "Multi-Voice Script" tab in the web app with:

Multi-voice script interface in eidosSpeech

📝 Feature #2: Automatic Subtitle Generation

Generate .srt subtitle files automatically with accurate timing. Perfect for video content creators who need subtitles for accessibility or engagement.

Why Subtitles Matter

How It Works

When you generate speech, eidosSpeech tracks word-level timing and creates an SRT file with accurate timestamps:

1
00:00:00,000 --> 00:00:02,500
Hello, welcome to eidosSpeech.

2
00:00:02,500 --> 00:00:05,000
This is an example subtitle file.

API Example

curl -X POST https://eidosspeech.xyz/api/v1/tts/subtitle \
  -H "X-API-Key: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Your text here",
    "voice": "en-US-JennyNeural"
  }'

# Response:
{
  "audio_url": "/cache/abc123.mp3",
  "subtitle": "1\\n00:00:00,000 --> 00:00:02,500\\nYour text here\\n"
}

🎨 Feature #3: Voice Styles & Emotions

Add emotions and speaking styles to supported voices. Make your content more engaging with cheerful, sad, angry, or whispering tones.

Supported Styles

We support 30+ voice styles across 10 voices, including:

Example Use Cases

API Example

curl -X POST https://eidosspeech.xyz/api/v1/tts \
  -H "X-API-Key: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "I am so excited about this!",
    "voice": "en-US-AriaNeural",
    "style": "excited",
    "style_degree": 1.5
  }' \
  --output excited.mp3

⚡ Feature #4: Voice Character Presets

We've curated 9 voice character presets for common use cases. One-click voice selection for:

Each preset includes pre-configured voice, speed, pitch, and style settings optimized for that use case.

📊 Feature #5: Audio Waveform Visualizer

See your audio visually with our new waveform visualizer. Features include:

⭐ Feature #6: Voice Favorites

Save your favorite voices for quick access. Features:

⌨️ Feature #7: Keyboard Shortcuts

Power users rejoice! We've added keyboard shortcuts for common actions:

🔗 Feature #8: Embeddable Widget

Embed eidosSpeech TTS directly on your website with our new widget:

<iframe 
  src="https://eidosspeech.xyz/embed?text=Hello&voice=en-US-JennyNeural"
  width="100%" 
  height="200"
  frameborder="0"
></iframe>

Perfect for:

🎯 Feature #9: Voice Comparison Tool

Compare multiple voices side-by-side before choosing. Generate the same text with different voices and listen to them back-to-back.

Performance & Scalability

Behind the scenes, we've made significant improvements:

Global Heavy Operation Limit

Multi-voice script generation is CPU-intensive. We've implemented smart queueing to prevent server overload:

Rate Limits

Multi-voice scripts have separate rate limits:

Health Monitoring

New /health endpoint shows server load:

{
  "status": "healthy",
  "load": {
    "heavy_operations_active": 2,
    "heavy_operations_max": 3,
    "heavy_operations_usage_pct": 66.7
  }
}

Migration Guide

All v2.1 features are backward compatible. Existing integrations continue to work without changes.

New Dependencies

If you're self-hosting, update your environment:

Environment Variables

New optional configuration:

MAX_HEAVY_OPERATIONS=3  # Concurrent multi-voice limit

What's Next?

We're already working on v3 with features like:

Try v2.1 Today

All v2.1 features are live and available now. No update required — just visit eidosspeech.xyz/app and start exploring.

Registered users get immediate access to all features. Anonymous users can try everything except multi-voice scripts.

Experience v2.1 Features Now

Multi-voice scripts, subtitles, voice emotions, and more.

Try Multi-Voice API Documentation

Feedback & Support

We'd love to hear what you think about v2.1:

Thank you for being part of the eidosSpeech community. Here's to creating amazing voice content together! 🎉

e
eidosSpeech Team
Building free tools for developers and creators

Related Articles

INTRODUCTION

Introducing eidosSpeech

Free TTS API with 1,200+ voices in 75+ languages
TUTORIAL

How to Use eidosSpeech API

Complete guide with code examples