# AI use cases for Fish Audio Hermes (100yenadmin/fish-audio-hermes) Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Use cases: 5 | Page: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/ A plugin for the Hermes Agent that gives it Fish Audio speech: text-to-speech, speech-to-text, a voice library, voice cloning and voice design. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Give your Hermes agent a spoken voice: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/give-hermes-agent-a-speaking-voice/ - Transcribe a recording with speakers and subtitles: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/transcribe-recordings-with-speakers-and-subtitles/ - Find a narrator voice and save it under a short name: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/find-and-save-a-narrator-voice/ - Clone or design a custom voice with approval: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/clone-or-design-a-custom-voice/ - Manage Fish voices for a remote agent in Desktop: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/manage-fish-voices-from-hermes-desktop/ ## How to give your Hermes agent a spoken voice with Fish Audio Hermes Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Install the Fish Audio plugin so voice replies and read-aloud use Fish Audio speech. **Who it is for:** A Hermes Agent user who wants replies, read-aloud and voice notes spoken aloud in the CLI or a messaging app. **The problem:** Hermes needs a speech provider and a saved key before it can speak, and the setup has several steps. **The outcome:** The agent speaks through Fish Audio, and the setup check confirms that one test synthesis works. ### Steps 1. Run `hermes plugins install fish-audio --enable` on the machine that runs Hermes. 2. Run `hermes fish login` and paste your key from https://fish.audio/app/api-keys. 3. Answer the provider prompt, or pass `--yes` if you want Fish Audio to replace another speech provider. 4. Run `hermes fish doctor` to make one short billed synthesis, or `hermes fish doctor --no-synth` to skip it. (inferred, check the README) 5. Ask the agent to read a short reply aloud and listen to the result. ### Prompt to paste into your agent ```text Using the repo 100yenadmin/fish-audio-hermes, install the Fish Audio plugin for Hermes Agent on and run the setup check with `hermes fish doctor --no-synth`. Expected output: the plugin is enabled and the status check reports no errors. Verify that `hermes fish status` shows Fish Audio as the speech provider. ``` ### Caveat Hermes 0.21.6 and newer ask before installing Python dependencies, and older Hermes versions install them without asking. Risk, credentials: Your Fish Audio API key is saved to the active Hermes profile, so do not paste it into chat; `/fish` refuses keys sent in chat. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/give-hermes-agent-a-speaking-voice/ ## How to transcribe a recording with speakers and subtitles with Fish Audio Hermes Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Turn a meeting or interview file into a transcript with speaker turns, timestamps and SRT subtitles. **Who it is for:** A person who has a meeting or interview recording and needs a written transcript and subtitle file. **The problem:** Manual transcription is slow, and plain transcripts often do not show who said what or when. **The outcome:** A transcript with speaker turns, timestamps and an SRT subtitle file for the recording. ### Steps 1. Install the plugin with `hermes plugins install fish-audio --enable` and save your key with `hermes fish login`. 2. Place the audio file, for example meeting.m4a, where the Hermes agent can read it. 3. Ask the agent: "Transcribe meeting.m4a with speakers and give me subtitles." 4. Check a few timestamps and speaker labels against the original audio before you share the transcript. ### Prompt to paste into your agent ```text Using the repo 100yenadmin/fish-audio-hermes, transcribe with the fish_transcribe tool, asking for speaker turns, timestamps and SRT output. Expected output: a transcript with speaker labels and an SRT subtitle file. Verify that the first and last timestamps match the start and end of the audio. ``` ### Caveat Speaker labels are produced by the transcription service, so check them against the recording before you rely on them. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/transcribe-recordings-with-speakers-and-subtitles/ ## How to find a narrator voice and save it under a short name with Fish Audio Hermes Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Search Fish Audio's community voices, choose one, and reuse it under a short name. **Who it is for:** A content creator who needs a consistent narrator voice for scripts, videos or audio posts. **The problem:** Finding a suitable voice in a large library takes time, and voice ids are hard to remember. **The outcome:** A chosen narrator voice is active for the profile and saved under a name such as narrator. ### Steps 1. Run `hermes plugins install fish-audio --enable` and `hermes fish login` if you have not set up the plugin. 2. In chat, run `/fish voices narrator` to search the voice library. 3. Run `/fish preview narrator` (or the voice id you found) to hear a short sample, which is a billed synthesis. 4. Run `/fish use ` to set the voice for this profile. (inferred, check the README) 5. Run `/fish alias add narrator ` so you can use the name `narrator` later. (inferred, check the README) ### Prompt to paste into your agent ```text Using the repo 100yenadmin/fish-audio-hermes, search the Fish Audio voice library for a deep British narrator and save the best match as the alias narrator with `/fish alias add`. Expected output: a voice id saved under the name narrator and shown by `/fish alias`. Verify that `/fish status` reports narrator as the active voice. ``` ### Caveat Previews are billed synthesis calls, so each sample you hear uses Fish Audio credit. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/find-and-save-a-narrator-voice/ ## How to clone or design a custom voice with approval with Fish Audio Hermes Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Create your own voice from a short sample or a written description, after you approve it. **Who it is for:** A creator or team lead who wants a branded or personal voice for an agent and has the speaker's permission. **The problem:** A stock voice may not fit the agent's role, and making a custom voice needs a clear consent step. **The outcome:** A cloned or designed voice saved to your Fish Audio account and available to Hermes. ### Steps 1. Set up the plugin with `hermes plugins install fish-audio --enable` and `hermes fish login`. 2. Get the speaker's permission and prepare one to three recordings, each up to 10 MB, for Desktop cloning. 3. In chat, ask the agent to clone the voice from your sample, or to design a voice from a written description. 4. Approve the clone request at Hermes's approval gate, which asks you first by default. 5. Pick the saved candidate you like and save it with a name for later use. ### Prompt to paste into your agent ```text Using the repo 100yenadmin/fish-audio-hermes, clone a voice from with the fish_voices tool and wait for my approval before the clone runs. Expected output: a new voice id in My voices. Verify that the speaker has given permission and that the new voice appears when you list your voices. ``` ### Caveat Cloning and deleting from chat go through Hermes's approval gate, and Desktop cloning needs the speaker's permission according to the README. Risk, voice cloning: Only clone a voice from a recording where the speaker has given permission, because a cloned voice can imitate a real person. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/clone-or-design-a-custom-voice/ ## How to manage Fish voices for a remote agent in Desktop with Fish Audio Hermes Repo: [100yenadmin/fish-audio-hermes](https://github.com/100yenadmin/fish-audio-hermes) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Install the plugin from Git into a remote Hermes agent and use the Voices page in Desktop. **Who it is for:** A Hermes Desktop user whose agent runs on another machine and who wants to browse, preview and pick voices from the Desktop app. **The problem:** The Desktop half of the plugin does not install itself for agents on another machine, so setup needs several steps. **The outcome:** The Voices page appears for the connected agent, and the agent speaks with the voice you pick. ### Steps 1. In Hermes Desktop, open Capabilities, then Plugins, then Install from Git. 2. Enter https://github.com/100yenadmin/fish-audio-hermes, choose Review repository, then Install. 3. On Desktop 0.21.7 and newer, use Enable after install. On older Desktop, switch on Desktop from the Fish Audio entry in Capabilities, then Plugins. 4. Restart the agent's gateway once, because Hermes mounts plugin routes only at startup. 5. Open the Voices page, search the library, preview a voice and choose Use. ### Prompt to paste into your agent ```text Using the repo 100yenadmin/fish-audio-hermes, install the plugin into the connected agent through Hermes Desktop and restart its gateway. Expected output: a Voices row for that agent in Desktop. Verify that the agent's status shows a Fish Audio key and a selected voice. ``` ### Caveat Desktop 0.21.5 has no plugin settings pages, so use the Voices page and `/fish` commands there. Risk, remote script: Desktop installs code from the GitHub repository into your connected agent, so review the repository before you choose Install. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/100yenadmin-fish-audio-hermes/manage-fish-voices-from-hermes-desktop/