Hermes Agent TTS Providers: Which One to Pick

Ten Providers, One Question: Which Is Right for You?

Hermes Agent supports ten text-to-speech providers. That gives you a choice of voice quality, cost, and privacy profile, from free local processing to premium cloud voices. This is the provider-comparison page in the voice cluster. For the feature overview, see what Hermes Agent voice mode can do; for configuration and troubleshooting, see the voice setup guide.

This post breaks down every supported provider, what it takes to set each one up, the quality trade-offs, and a clear recommendation for each type of use case.

The Full Provider List

Four providers require no API key and no cost. Six require credentials and charge per character or per request. The right choice depends on whether you want zero friction, maximum quality, or something in between.

Free Providers

Edge TTS

Edge TTS is the default provider and the best starting point for most users. It uses Microsoft's neural speech synthesis infrastructure, requires no API key, no extra installation, and no cost.

It supports 322 voices across 74 languages, making it a practical multilingual starting point without a provider key.

Configuration in ~/.hermes/config.yaml:

tts:
  provider: edge

That is it. If you have not configured TTS before, Hermes is already using Edge TTS by default.

NeuTTS

NeuTTS is the best free option for users who want fully local processing - nothing leaves your machine. It runs a neural TTS model locally via llama.cpp-style inference with GPU or CPU acceleration.

Setup requires a few extra steps compared to Edge TTS:

python -m pip install -U neutts[all]
sudo apt install espeak-ng   # Linux
brew install espeak-ng        # Mac

Then configure in config.yaml:

tts:
  provider: neutts
  neutts:
    model: neuphonic/neutts-air-q4-gguf
    device: cpu   # or cuda if you have a compatible GPU

Telegram users: NeuTTS outputs WAV files. Telegram requires Opus for voice bubbles. Hermes handles the conversion automatically if ffmpeg is installed:

sudo apt install ffmpeg   # Linux
brew install ffmpeg        # Mac

NeuTTS also supports voice cloning. Provide a short audio sample and its transcript:

tts:
  provider: neutts
  ref_audio: /path/to/your-voice-sample.wav
  ref_text: "This is the reference transcript for voice matching."

Piper and KittenTTS

Piper is a fast, lightweight offline TTS engine originally developed for Home Assistant. KittenTTS is a newer local option with a similar philosophy. Both work without an internet connection after the initial model download and are good choices for resource-constrained environments or always-offline deployments.

Paid Providers

ElevenLabs

ElevenLabs produces the most natural-sounding voices available and has become the default choice for content creators who need audio that sounds human. If you are using your Hermes agent in customer-facing scenarios or producing audio content, ElevenLabs is the clear leader.

Setup:

pip install "hermes-agent[tts-premium]"

Add to ~/.hermes/.env:

ELEVENLABS_API_KEY=your_key_here

Configure in config.yaml:

tts:
  provider: elevenlabs
  elevenlabs:
    voice_id: pNInz6obpgDQGcFmaJgB   # Adam
    model_id: eleven_multilingual_v2

The voice_id is the main lever. ElevenLabs has hundreds of pre-built voices and supports cloning a custom voice from a short audio sample. Browse the voice library at elevenlabs.io and paste the ID into your config.

ElevenLabs produces Opus audio natively, which means no conversion step for Telegram voice bubbles - responses arrive faster compared to NeuTTS. Pricing is usage-based. For a personal agent with moderate traffic, the free tier (10,000 characters/month) is often enough.

OpenAI TTS

If you are already paying for OpenAI API access, TTS is a natural addition. OpenAI's six voices (alloy, echo, fable, onyx, nova, shimmer) are high quality, low latency, and consistent across languages.

Add to ~/.hermes/.env:

VOICE_TOOLS_OPENAI_KEY=your_key_here

Configure:

tts:
  provider: openai
  openai:
    model: gpt-4o-mini-tts
    voice: nova

OpenAI TTS provides a consistent cloud option. Check the current OpenAI and Hermes documentation for available voices, models, and pricing before choosing it for a production workflow.

MiniMax, Mistral, Gemini, and xAI

These are paid options alongside the free local and Edge providers. Their voice catalogues, models, regions, and pricing change independently. Use the current Hermes provider reference to find the required environment variable and configuration block, then validate a short Telegram message before committing to one.

Which Provider Should You Choose?

Zero setup, zero cost - Edge TTS. Already configured, nothing to install.

Zero cost, local processing, privacy-first - NeuTTS with espeak-ng and ffmpeg.

Best voice quality, do not mind paying - ElevenLabs with a custom voice ID from the voice library.

Already on OpenAI's API - OpenAI TTS. Consistent and fast, reuses existing credentials.

Broad multilingual options - compare MiniMax, Mistral, Gemini, and the available Edge voices using the current provider documentation for the languages you need.

Customer-facing or content creation use cases - ElevenLabs or OpenAI TTS. The quality difference over Edge TTS is clearly audible in these contexts.

Switching Providers

Switching begins with the provider field in config.yaml. Add the required credential where applicable, then restart the gateway and test a short voice reply. Local providers can require extra system dependencies, so follow the current Hermes provider guide before assuming a switch is configuration-only.

Testing Your TTS Setup

From the Hermes CLI:

hermes
> /voice on
> Hello, this is a TTS test.

The agent will respond with spoken audio. If you hear nothing, confirm your system audio output is routed correctly and the provider's API key is present in .env.

Running Hermes Without the Configuration Overhead

Configuring TTS manually is straightforward, but it is still a setup step with platform-specific dependencies, particularly format conversion for Telegram voice bubbles. If you would rather not maintain the Hermes runtime and gateway, explore Hermify: a managed Hermes Agent you primarily use from Telegram and can configure from the web app. Check the current product settings for the voice workflow you need rather than assuming a provider is enabled by default.

Sources

• Hermes Agent TTS documentation
• Hermes Agent voice mode guide
• GitHub: TTS Speed Control issue
• GitHub: Google Gemini TTS feature request