Social Stream Ninja - TTS Voice Guide

Overview

Social Stream Ninja offers multiple Text-to-Speech (TTS) options, from free system voices to premium services. This guide covers everything you need to know about configuring and using TTS effectively.

Quick Start: Add ?speech=en-US to your URL to enable English TTS

Where is TTS Used?

Social Stream Ninja: Reads out audience chat messages in multiple areas
CAPTION.Ninja: Offers closed-captioning, transcription, and translation with TTS
Both services offer premium and free TTS options

Free TTS Limitations:

OBS browser sources cannot capture system TTS audio directly
Requires complex audio routing solutions
Limited browser support (Opera, Firefox may lack TTS)
Premium services are recommended for easier integration

TTS Provider Options

System TTS (Free)

Uses your operating system's built-in voices
Limited language support based on system installation
Audio plays through system speakers - requires special capture methods
Browser compatibility varies significantly

Local / Free TTS Options (No API Key Required)

Want fully local AI TTS? Several high-quality AI voices are built directly into Social Stream Ninja and run in your browser — no API key, no cloud, no extra install. See the Local AI TTS Guide for setup instructions and self-hosted server options.

Provider	Cost	OBS Capture	Features
Kokoro TTS	Free	Direct	Browser-based AI, excellent quality, 26 voices
Piper TTS	Free	Direct	Browser-based, fast, CPU-friendly neural TTS
Kitten TTS	Free	Direct	Browser-based, lightweight ONNX model
eSpeak-NG	Free	Direct	Classic open-source, works on any hardware

Premium / Cloud TTS Options (Direct Browser Audio)

Provider	Cost	OBS Capture	Features
OpenAI TTS	API costs apply (or free local)	Direct	High quality; also supports local servers via custom endpoint
Google Cloud	API costs apply	Direct	Professional quality, multiple languages
ElevenLabs	Free tier available	Direct	Custom voice training, natural sounding
Speechify	API costs apply	Direct	High-quality voices, multiple languages
Gemini TTS	API costs apply	Direct	Google generative language API

Browser Support

Chrome

✓ Full Support

Google-powered voices + system voices

Edge

✓ Full Support

Microsoft voices + Windows TTS packs

Firefox

⚠ Limited Support

Local system languages only

Opera

✗ No Support

May lack TTS functionality

Browser Limitations:

Not all browsers support text-to-speech (Opera, some Firefox versions)
Chrome offers Google-powered TTS options
Edge supports Microsoft TTS and Windows language pack voices
Safari requires user interaction to start audio
Check available voices for your browser

Windows TTS Audio Capture Methods for OBS

Premium TTS Services (Recommended)

All premium services play audio directly through the browser:

Simply enable "Control audio via OBS" in browser source
No virtual audio cables needed
Works with SSN app and OBS browser sources

System TTS Capture Methods

Important: OBS Studio's browser source cannot capture system-level TTS audio directly. This limitation affects all browsers and requires special audio routing methods.

Free text-to-speech comes with limitations:

Cannot be captured directly by OBS browser sources
Limited support across browsers (Opera, Firefox may lack TTS)
Chrome offers Google-powered options, Edge has Microsoft options
Requires complex audio routing for capture

Routing downloads: VB-Audio Virtual Cable | Voicemeeter | Audio Router (legacy)

Method 1: Default Audio Route (Most Common)

1. Set VB-Audio Virtual Cable as Windows default output - Sound Settings > Output > CABLE Input 2. OBS: - Add Audio Input Capture - Source: CABLE Output - Monitor: Monitor and Output, or Monitor Only if another source handles stream output

Method 2: Windows 10 App Route

1. Sound Settings > App volume and device preferences 2. Find browser in list 3. Output: CABLE Input 4. OBS setup same as Method 1

Method 3: Windows 11 App Route

1. Settings > System > Sound > Volume Mixer 2. Locate browser 3. Output: CABLE Input 4. OBS setup same as Method 1

Method 4: Audio Router Software

1. Install Audio Router 2. Route browser to CABLE Input 3. OBS setup same as Method 1

Method 5: Voicemeeter (Advanced)

1. Install Voicemeeter 2. Set as Windows default output 3. Route: - Hardware out > speakers - Virtual out > OBS 4. OBS captures Voicemeeter output

Testing Your Setup

1. Play TTS 2. Check OBS meter 3. Verify system audio 4. Adjust levels if needed

Alternatives: If these methods don't work, consider using premium options (Google Cloud, ElevenLabs, Speechify) or explore self-hosted open-source TTS solutions.

Installing Additional Language Packs

Windows 11

Navigate to Start > Settings > Time & Language > Speech
Under Manage Voices, click Add Voices
Select desired languages and click Add
Restart browsers to refresh available voices

Windows 10

Follow Microsoft's official guide for installing language packs.

Tip: Some third-party voices may not appear in browsers due to compatibility issues. Firefox often shows more system voices than Chromium-based browsers.

URL Parameters for TTS Configuration

Basic Parameters

Parameter	Description	Example
&speech	Enable TTS with language code	&speech=en-US
&pitch	Voice pitch (0.1 to 2.0)	&pitch=1.2
&volume	Volume level (0.0 to 1.0)	&volume=0.8
&rate	Speaking rate (0.1 to 10.0)	&rate=1.5
&voice	Partial voice name match	&voice=google
&ttsprovider	Select provider: kokoro, piper, kitten, espeak, openai, customtts, localtts, elevenlabs, google, speechify, gemini	&ttsprovider=customtts

Advanced Parameters

Parameter	Description
&simpletts	Don't say "says" or "someone says"
&simpletts2	Don't read chatnames at all
&ttscommand	Enable custom TTS command (default: !say)
&readevents	Include stream events in TTS
&skipmessages=3	Read every 3rd message only

TTS Provider Configuration

Kokoro TTS (Free, Built-in)

Enable with ?ttsprovider=kokoro
Runs in browser via WebGPU/WASM — no server needed
Works directly with OBS browser source
Voice selection: &voicekokoro=af_bella
Speed control: &kokorospeed=1.2
Kokoro's built-in voices are English voices; &speech=pt-BR, &speech=es-ES, or matching &language= values will not turn Kokoro into Portuguese or Spanish TTS

Piper TTS (Free, Built-in)

Enable with ?ttsprovider=piper
Fast, CPU-friendly neural TTS running in browser
Voice selection: &pipervoice=en_US-hfc_female-medium
Portuguese voices: &pipervoice=pt_BR-faber-medium or &pipervoice=pt_BR-edresson-low
Spanish voices: &pipervoice=es_ES-davefx-medium or &pipervoice=es_MX-ald-medium
Speed control: &piperspeed=1.0

Kitten TTS (Free, Built-in)

Enable with ?ttsprovider=kitten
Lightweight ONNX-based TTS running in browser
Voice selection: &kittenvoice=expr-voice-4-f

eSpeak-NG (Free, Built-in)

Enable with ?ttsprovider=espeak
Classic open-source TTS, works on any hardware
Voice selection: &espeakvoice=en
Portuguese example: &speech=pt-BR&ttsprovider=espeak&espeakvoice=pt-br
Spanish example: &speech=es-ES&ttsprovider=espeak&espeakvoice=es
Speed control: &espeakspeed=175

Portuguese and Spanish TTS Examples

Portuguese, best free local quality tested in SSN: ?speech=pt-BR&ttsprovider=piper&pipervoice=pt_BR-faber-medium
Portuguese, fastest fallback tested in SSN: ?speech=pt-BR&ttsprovider=espeak&espeakvoice=pt-br
Spanish, best free local quality tested in SSN: ?speech=es-ES&ttsprovider=piper&pipervoice=es_ES-davefx-medium
Spanish, fastest fallback tested in SSN: ?speech=es-ES&ttsprovider=espeak&espeakvoice=es
For cloud voices, use a provider voice/language that supports the target language, such as Google Cloud, ElevenLabs, Speechify, Gemini, or an OpenAI-compatible local server.

OpenAI / Local Server TTS

Enable with ?ttsprovider=openai
Use ?ttsprovider=customtts or ?ttsprovider=localtts for a self-hosted endpoint
Uses OpenAI's API by default, or any compatible local server
Custom endpoint: &openaiendpoint=http://localhost:8880/v1/audio/speech
Important: localhost and 127.0.0.1 mean the same computer that is playing the TTS page. If OBS is on a different computer than your TTS server, use the server computer's LAN IP instead.
No API key needed for local servers
If the local server has CORS or local network problems in Chrome/OBS, run npm run local-tts-bridge on the OBS computer and point SSN at http://127.0.0.1:8124/v1/audio/speech
SSN sends { model, input, voice, response_format, speed } and supports binary audio, JSON audio URLs, and JSON base64 audio
Custom/local endpoint playback is buffered today; SSN does not progressively play streamed audio chunks yet
Voice: &voiceopenai=af_bella, speed: &openaispeed=1.0. Use a voice name your server supports; Kokoro voices look like af_bella, while openedai-speech/OpenAI-style voices may look like nova or echo.
See the Local AI TTS Guide for self-hosted server setup

Google Cloud TTS

Enable with ?ttsprovider=google&ttskey=YOUR_API_KEY
Professional quality voices
Voice selection: &voicegoogle=en-GB-Standard-A
Language: &googlelang=en-US

Gemini TTS

Enable with ?ttsprovider=gemini&geminikey=YOUR_API_KEY
Model: &geminimodel=gemini-2.5-flash-preview-tts
Voice: &voicegemini=Kore, language: &geminilang=th-TH
Style instructions: &geministyle=Read aloud in a warm tone.

ElevenLabs TTS

Enable with ?ttsprovider=elevenlabs&elevenlabskey=YOUR_API_KEY
Voice ID: &voice11=YOUR_VOICE_ID
Model: &elevenlabsmodel=eleven_multilingual_v2
Parameters: stability, similarity, style can be adjusted

Speechify TTS

Enable with ?ttsprovider=speechify&speechifykey=YOUR_API_KEY
Voice: &voicespeechify=henry
Model: &speechifymodel=simba-english

Troubleshooting

Common Issues

No audio playing: Check that TTS is enabled, the TTS-producing page is open, and the browser source is not muted. In a normal browser, click the page once.
Voices not showing: Restart browser after installing language packs
OBS not capturing: For browser/provider TTS, check Control audio via OBS. For system TTS, use one of the capture methods above
Local endpoint works in the app test but not OBS: OBS is a separate browser. Check the endpoint from the OBS computer, especially if using 127.0.0.1.
Only the first letter or first words are read: remove ttsquick from the OBS URL if present.
Safari issues: Safari has limited automatic TTS support
Premium service not working: Check API key and ensure provider is correctly specified

Best Practices

Use premium TTS services for easiest OBS integration
Test your setup with simple phrases before going live
Consider user-generated content risks with TTS
Have a toggle to quickly disable TTS if needed

Test Your Browser's TTS Support

Click the button below to see available voices in your browser: