DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to transcribe voice messages with tuned speech settings with Hermes Speech

Set an AllModels speech-to-text model and adjust language and prompt hints.

  • Content
  • Intermediate
  • 15 minutes
  • From the README
  • Any agent

Authorization notice. Hermes Speech is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA Hermes user who receives voice messages through a gateway and needs accurate transcripts for names or terms in their work.

The problemVoice messages with product names or a specific language can transcribe poorly with default settings.

The outcomeVoice messages transcribe through the chosen AllModels STT model with your language and term hints applied.

What you need first

  • Hermes Agent 0.20.0 or later
  • An AllModels account, created through the email signup the plugin starts when no ALLMODELS_API_KEY is set
  • Terminal access to run hermes plugins install, or a Hermes session where you can send the install message

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 for your agent

Using the hermes-speech plugin from allmodels-io/hermes-speech, set the speech-to-text model and language for <target language> and add the prompt terms <target 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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page