Pannelai Stt

Speech-to-text through pannelAI. Covers POST /api/v1/audio/transcriptions as a multipart upload, the model and language fields, and the verbatim upstream answer. Use when a client needs an audio file transcribed by the gateway.

49 stars 6 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add rusmanadodi2598/pannelAI --skill pannelai-stt
Manual install
git clone --depth 1 https://github.com/rusmanadodi2598/pannelAI.git /tmp/pannelAI
mkdir -p ~/.claude/skills
cp -r /tmp/pannelAI/skills/pannelai-stt ~/.claude/skills/pannelai-stt

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# pannelAI: Speech-to-Text

One route: `POST /api/v1/audio/transcriptions`, a multipart upload, gateway-key auth.

```bash
curl -s $PANNELAI_URL/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $PANNELAI_KEY" \
  -F "file=@clip.mp3" \
  -F "model=deepgram/nova-3" \
  -F "language=id"
```

The upload is multipart, not JSON, so `-F` rather than `-d`. The file part carries the audio bytes and
their content type.

## Fields

| Field | Required | Notes |
|---|---|---|
| `file` | yes | The audio. |
| `model` | yes | `provider/model`. The provider must declare STT support. |
| `language` | no | The spoken language, as a code. |
| `prompt` | no | Context to bias the transcription. |
| `response_format` | no | The shape to ask for, where the provider supports more than one. |
| `temperature` | no | Decoding temperature, where the provider supports it. |

`language`, `prompt`, `response_format`, and `temperature` are forwarded to OpenAI-compatible providers,
which is where the reference forwards them. A provider-specific adapter reads the subset it declares, so
a field the provider ignores is not an error.

## The answer

The gateway forwards the upstream's answer verbatim rather than re-encoding it, because re-encoding would
drop whichever fields the caller asked for with `response_format`:

- a JSON answer arrives as `application/json`, usually `{"text": "..."}`
- anything else arrives as `text/plain`
Read the full skill on GitHub

Details

Skill name
pannelai-stt
Path
skills/pannelai-stt/SKILL.md
License
MIT
Repo updated
24 October 2026

FAQ

What does the Pannelai Stt skill do?

Speech-to-text through pannelAI. Covers POST /api/v1/audio/transcriptions as a multipart upload, the model and language fields, and the verbatim upstream answer. Use when a client needs an audio file transcribed by the gateway.

How do I install the Pannelai Stt skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add rusmanadodi2598/pannelAI --skill pannelai-stt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Pannelai Stt popular?

It lives in rusmanadodi2598/pannelAI, which has 49 GitHub stars and 6 forks.

Related skills

Pannelai

49

rusmanadodi2598/pannelAI

Entry point for pannelAI, a self-hosted AI gateway that speaks OpenAI, Anthropic, and OpenAI Responses wire formats for chat, image generation, text-to-speech, speech-to-text, embeddings, and web search. Use when the user mentions pannelAI, a gateway base URL, or wants one key in front of several providers. Covers setup, gateway-key auth, model discovery, and links to one skill per capability.

Images, Video & Audio

Pannelai Chat

49

rusmanadodi2598/pannelAI

Chat and code generation through pannelAI, in the OpenAI chat completions, Anthropic messages, or OpenAI Responses wire format, streamed or not. Covers the model field, streaming, combo routing, and the vision adapter. Use when a client needs an LLM answer from the gateway.

AI, LLMs & Agents

Pannelai Embeddings

49

rusmanadodi2598/pannelAI

Embeddings through pannelAI. Covers POST /api/v1/embeddings, the provider/model string, the input field, and the OpenAI embeddings answer with its usage block. Use when a client needs vectors for RAG or semantic search from the gateway.

AI, LLMs & Agents

Pannelai Tts

49

rusmanadodi2598/pannelAI

Text-to-speech through pannelai. Covers POST /api/v1/audio/speech, the voice catalog at GET /api/v1/audio/voices, the bytes-versus-base64 response choice, and the per-provider adapters. Use when a client needs spoken audio from the gateway.

Images, Video & Audio

Pannelai Image

49

rusmanadodi2598/pannelAI

Text-to-image and async video generation through pannelAI. Covers POST /api/v1/images/generations, the provider/model string, the prompt and size fields, the normalized OpenAI images answer, and the two video job routes. Use when a client needs a generated image or video from the gateway.

Images, Video & Audio

Remove Background

44

pilioai/skills

Remove an image background with the Pilio developer API. Use when the user wants transparent-background cutouts, portrait or product background removal, or automated image background cleanup through Pilio.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.