How-To Series · 4: Eyes, Ears, Voice

Text-to-Speech (TTS)

Voice output and voice message transcription across all platforms

After this videoConvert text to speech with ten providers and transcribe voice messages automatically

Hermes Agent supports both text-to-speech output and voice message transcription across all messaging platforms. Convert text to speech with ten providers including Edge TTS, ElevenLabs, OpenAI TTS, MiniMax TTS, Mistral (Voxtral TTS), Google Gemini TTS, xAI TTS, NeuTTS, KittenTTS, and Piper.

About these resources. This episode covers Hermes' text-to-speech and voice message transcription features, showing how to configure different providers and deliver voice messages across platforms.

New words here · Plain English

one sentence each · full glossary
TTSText-to-Speech: converting written text into spoken audio. Hermes can read its replies out loud.
TranscriptionConverting spoken audio into written text. Hermes can transcribe voice messages you send it.

Sources · What this video distills

1 docs page · every command below traces to one of them
Primary guide
Text-to-Speech (TTS)
Read ↗

Next in the series · Episodes that build on this