Cells for speech: text to speech, live voice, phone calls and music.

1. elevenlabs-musicby NousResearch · rewrite of NousResearch/hermes-official-pluginsElevenLabs Music: songs, edits, stems and video scores from the ElevenLabs Music API725Voice
2. sound-effectsby NousResearch · rewrite of NousResearch/hermes-official-pluginsElevenLabs sound effects: a described sound becomes an audio file, kept in this profile's library725Voice
3. talkby TheSmokeDev · rewrite of TheSmokeDev/hermes-talkSpeak text aloud, transcribe an audio file, or record and transcribe a question200Voice
4. speechby allmodels-io · rewrite of allmodels-io/hermes-speechAllModels speech: one key for text-to-speech, speech-to-text and voice search194Voice
5. fish-audioby 100yenadmin · rewrite of 100yenadmin/fish-audio-hermesFish Audio: text to speech, dictation and the voice library, as tools a model calls69Voice
6. live-voiceby Synero · rewrite of Synero/hermes-live-voiceLive voice: dictate from the microphone and hear the agent's answers spoken43Voice
7. omnivoiceby ThaungThanHan · rewrite of ThaungThanHan/hermes-omnivoiceOmniVoice speech on this machine: a text becomes an audio file, by voice design or a reference clip18Voice
8. call-meby radres · rewrite of radres/hermes-plugin-call-me/call-me: ring a phone, speak a sentence, read the spoken answer back as text16Voice
9. alice-voiceby bablobanov · rewrite of bablobanov/hermes-alice-voiceA Yandex Alice voice skill's requests, answered as turns in one session12Voice
10. phone-callby winchxyz · rewrite of winchxyz/hermes-phonePhone Call: an approved outbound call with an AI disclosure, and what came of it10Voice
11. gemini-liveby skappafrost · rewrite of skappafrost/hermes-gemini-liveGemini Live voice: one spoken turn per call, the reply saved as a WAV, and the work the voice model delegates named back to you6Voice
12. ghost-callby winchxyz · rewrite of winchxyz/hermes-ghost-callGhost Call: one-line hints while the operator is on a call, and a post-call summary5Voice
13. kokoro-ttsby brunosouzas · rewrite of brunosouzas/hermes-kokoro-ttsKokoro: local text-to-speech through a server on loopback, one voice per language4Voice
14. deepgram-voiceby jaysonsantos · rewrite of jaysonsantos/hermes-deepgram-voice-pluginDeepgram Aura speech and Nova transcription: text becomes audio, a recording becomes text3Voice
15. openrouter-voiceby esketids · rewrite of esketids/hermes-openrouter-voiceOpenRouter voice: transcribe an audio file to text and speak text as an mp3, on a key3Voice
16. gemini-live-bridgeby cruzlxyz · rewrite of cruzlxyz/gemini-live-bridgeGemini Live: one duplex session with the Live API, its model catalog and its token meter2Voice
17. voicestudioby aska-digital · rewrite of aska-digital/protean-voice-studioVoiceStudio: speak, design voices, render chaptered audiobooks and dub videos through a local VoiceStudio server2Voice
18. emotion-chipby 100yenadmin · rewrite of 100yenadmin/ai-emotion-chipEmotion Chip: the agent's bracket delivery cues, rendered for Fish Audio or ElevenLabs, or stripped.1Voice
19. sonioxby XimilalaXiang · rewrite of XimilalaXiang/hermes-sonioxSoniox voice: text becomes a spoken audio file, a recording becomes text1Voice
20. ttsbuddyby ngelik · rewrite of ngelik/ttsbuddy-cliTTS Buddy speech: synthesize an MP3, pick a voice, recover a job1Voice