Voice & TTS
Voice & TTS
Start with meaning, then move to detail.
This lesson explains Voice & TTS as part of extending Hermes and connecting external tools. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect Text-to-Speech, Platform Delivery, Configuration, then verify failure modes and version compatibility.
Complete installation and one successful task before adding new capabilities.
A clear outcome before you read.
- Understand Voice & TTS without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Provider
- The service that runs or provides access and authentication to a model.
Text-to-speech and voice message transcription across all platforms
What does the source say, and in what order?
- 01Text-to-Speech
Start here to understand the core idea or structure.
- 02Platform Delivery
Read this after the foundation, then connect it to the previous step.
- 03Configuration
Read this after the foundation, then connect it to the previous step.
- 04Gemini Persona Prompts
Read this after the foundation, then connect it to the previous step.
- 05Audio Tags (Gemini, xAI)
Read this after the foundation, then connect it to the previous step.
- 06Input length limits
Read this after the foundation, then connect it to the previous step.
- 07Telegram Voice Bubbles & ffmpeg
Read this after the foundation, then connect it to the previous step.
- 08xAI Custom Voices (voice cloning)
Read this after the foundation, then connect it to the previous step.
- 09Piper (local, 44 languages)
Read this after the foundation, then connect it to the previous step.
- 10Custom command providers
Finish here to verify the result and special cases.
Copy only after you understand the effect.
# In ~/.hermes/config.yaml
tts:
provider: "edge" # "edge" | "elevenlabs" | "openai" | "minimax" | "mistral" | "gemini" | "xai" | "deepinfra" | "neutts" | "kittentts" | "piper"
speed: 1.0 # Global speed multiplier (provider-specific settings override this)
edge:
voice: "en-US-AriaNeural" # 322 voices, 74 languages
speed: 1.0 # Converted to rate percentage (+/-%)
elevenlabs:
voice_id: "pNInz6obpgDQGcFmaJgB" # Adam
model_id: "eleven_multilingual_v2"
openai:
model: "gpt-4o-mini-tts"
voice: "alloy" # tts:
provider: gemini
gemini:
voice: Algieba
persona_prompt_file: ~/.hermes/tts/butler-voice.mdtts:
provider: gemini
gemini:
model: gemini-3.1-flash-tts-preview
audio_tags: true
xai:
auto_speech_tags: trueRead the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.