# AI use cases for Hermes Speech (allmodels-io/hermes-speech) Repo: [allmodels-io/hermes-speech](https://github.com/allmodels-io/hermes-speech) | Use cases: 4 | Page: https://dedupedai.com/use-cases/allmodels-io-hermes-speech/ Hermes Speech is a Python plugin that gives the Hermes Agent native text-to-speech and speech-to-text through AllModels, with voice search, previews, and conversational setup. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Add spoken replies to Hermes Agent: https://dedupedai.com/use-cases/allmodels-io-hermes-speech/add-spoken-replies-to-hermes/ - Find and preview a voice by description: https://dedupedai.com/use-cases/allmodels-io-hermes-speech/find-and-preview-a-voice/ - Transcribe voice messages with tuned speech settings: https://dedupedai.com/use-cases/allmodels-io-hermes-speech/transcribe-voice-messages-with-tuned-settings/ - Check speech balance and create a top-up link: https://dedupedai.com/use-cases/allmodels-io-hermes-speech/check-balance-and-top-up-speech-credits/ ## How to add spoken replies to Hermes Agent with Hermes Speech Repo: [allmodels-io/hermes-speech](https://github.com/allmodels-io/hermes-speech) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Install the plugin and turn on voice mode so Hermes reads its answers aloud. **Who it is for:** A Hermes Agent user who wants replies read aloud in the CLI, desktop app, or messaging gateway after a short setup. **The problem:** Hermes Agent can reply in text only until a speech provider is registered and voice mode is turned on. **The outcome:** Hermes speaks its streamed replies sentence by sentence through an AllModels voice. ### Steps 1. Run `hermes plugins install allmodels-io/hermes-speech --enable` in a terminal, or send the install message to your Hermes agent. 2. Restart the running Hermes CLI, desktop backend, or gateway. 3. Run `/speech` and complete the AllModels email signup if no API key is configured. 4. Run `/voice on`. 5. Run `/voice tts`. ### Prompt to paste into your agent ```text Using the hermes-speech plugin from allmodels-io/hermes-speech, enable spoken replies in . Expected output: Hermes reads its next reply aloud after /voice on and /voice tts. Verify by running /speech test Hello from Hermes and confirming that audio is returned. ``` ### Caveat The model and voice catalogues change over time, so the AllModels catalogues are the source of truth for which models are currently available. Risk, credentials: Signup uses your email and a single-use verification code, and the API key is stored in the profile's .env file as ALLMODELS_API_KEY. 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/allmodels-io-hermes-speech/add-spoken-replies-to-hermes/ ## How to find and preview a voice by description with Hermes Speech Repo: [allmodels-io/hermes-speech](https://github.com/allmodels-io/hermes-speech) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Search AllModels voices in plain language, hear samples, then pick one. **Who it is for:** A content creator or narrator who needs a voice with a specific tone, language, or accent and wants to hear options before choosing. **The problem:** Browsing a large voice list by name is slow, and choosing a voice blind risks a poor fit for the audio. **The outcome:** You select a voice that matches your description after hearing a sample of it. ### Steps 1. Run `/speech tts voice search` and describe the voice you want, for example British female narrator. 2. Run `/speech tts voice preview` and add a short sample sentence to hear the candidate. 3. Ask Hermes to switch to the voice you prefer, or repeat the search with different wording. 4. Run `/speech test Hello from Hermes` to confirm the chosen voice plays through Hermes. ### Prompt to paste into your agent ```text Using the hermes-speech plugin from allmodels-io/hermes-speech, search for a voice that matches and preview one candidate. Expected output: a short MP3 sample returned through Hermes MEDIA delivery, with the configured voice unchanged. Verify that the preview did not change the configured TTS model, voice, speed, or format. ``` ### Caveat Natural-language search runs on the AllModels server, so results depend on that catalogue at the time of the query. Risk, voice cloning: Search can return voices that imitate real people, so use a voice only if you have the rights to use it for your purpose. 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/allmodels-io-hermes-speech/find-and-preview-a-voice/ ## How to transcribe voice messages with tuned speech settings with Hermes Speech Repo: [allmodels-io/hermes-speech](https://github.com/allmodels-io/hermes-speech) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Set an AllModels speech-to-text model and adjust language and prompt hints. **Who it is for:** A Hermes user who receives voice messages through a gateway and needs accurate transcripts for names or terms in their work. **The problem:** Voice messages with product names or a specific language can transcribe poorly with default settings. **The outcome:** Voice messages transcribe through the chosen AllModels STT model with your language and term hints applied. ### Steps 1. Run `/speech stt model` and choose an AllModels speech-to-text model. 2. Run `/speech advanced language ja` or another language code you need. 3. Run `/speech advanced prompt Product names: Hermes, AllModels` with the terms you want recognized. 4. Send a voice message through a Hermes messaging gateway and check the transcript. ### Prompt to paste into your agent ```text Using the hermes-speech plugin from allmodels-io/hermes-speech, set the speech-to-text model and language for and add the prompt terms . Expected output: a confirmed STT model and settings. Verify by sending one test voice message and checking that the transcript contains the listed terms. ``` ### Caveat The README says the plugin uses Hermes standard transcription interfaces, so exact transcription behavior depends on the chosen AllModels STT model. 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/allmodels-io-hermes-speech/transcribe-voice-messages-with-tuned-settings/ ## How to check speech balance and create a top-up link with Hermes Speech Repo: [allmodels-io/hermes-speech](https://github.com/allmodels-io/hermes-speech) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Check the AllModels balance from Hermes and generate a top-up link when needed. **Who it is for:** A person or team running Hermes speech who needs to avoid running out of AllModels credit during regular use. **The problem:** Speech generation can stop when the account balance is low, and finding the balance and top-up path takes manual steps. **The outcome:** You know the current balance and have a top-up link for the amount you choose. ### Steps 1. Run `/speech balance` to see the current AllModels balance. 2. Run `/speech topup 25` to create a top-up link for 25 dollars. 3. Open the link and complete the top-up through AllModels. 4. Run `/speech balance` again to confirm the new balance. ### Prompt to paste into your agent ```text Using the hermes-speech plugin from allmodels-io/hermes-speech, check the AllModels balance and create a top-up link for . Expected output: the current balance and a top-up link. Verify that the balance increases after the top-up is completed. ``` ### Caveat The README gives the top-up example in dollars through the /speech topup command, so check the amount and currency shown on the AllModels page before paying. 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/allmodels-io-hermes-speech/check-balance-and-top-up-speech-credits/