skills.rest
diegosouzapw
diegosouzapwCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

omniroute-stt

Provides speech-to-text transcription and translation via OmniRoute-compatible endpoints with provider auto-fallback.

44.0k|5.9k|Updated Feb 13, 2026
Search Tags:#translation#transcription#audio#api gateway#fallback#speech-to-text#stt providers
One-click install
npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-stt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: omniroute-stt
Source: https://github.com/diegosouzapw/OmniRoute/tree/main/skills/omniroute-stt
Command: npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-stt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OmniRoute STT turns audio files or live speech into readable text without you having to pick and manage a single speech-to-text provider.

Core Features & Use Cases

  • Auto-fallback across multiple STT providers: Routes transcription to Whisper, AssemblyAI, Deepgram, and Azure STT for improved reliability.
  • OpenAI-compatible endpoints: Uses /v1/audio/transcriptions and /v1/audio/translations so you can drop it into existing OpenAI-style workflows.
  • Rich output formats: Produces common transcription responses like text, json, srt, vtt, and verbose_json with optional segment timing.

Quick Start

Use the OmniRoute endpoint to transcribe an audio file by sending a multipart request to /v1/audio/transcriptions with your OMNIROUTE_KEY and the file attached as [email protected].

Frequently Asked Questions about omniroute-stt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio files with automatic STT provider fallback?▼

To transcribe audio files with automatic STT provider fallback, send a multipart request to the /v1/audio/transcriptions endpoint with your OMNIROUTE_KEY and the audio file attached.

Can I use OpenAI-compatible endpoints to translate spoken audio to English?▼

Yes, you can use the OpenAI-compatible /v1/audio/translations endpoint to translate spoken audio content to English within your existing production pipelines.

What response formats are supported for speech-to-text transcription?▼

Speech-to-text transcription supports multiple response formats including text, json, srt, vtt, and verbose_json with optional segment timing for flexible output handling.

Do I need specific authentication to use OmniRoute for transcription?▼

Yes, you need to configure OMNIROUTE_URL and OMNIROUTE_KEY authentication parameters to access the OmniRoute-compatible transcription and translation endpoints.

How does auto-fallback improve audio transcription reliability across providers?▼

Auto-fallback improves audio transcription reliability by routing requests across multiple STT providers like Whisper, AssemblyAI, Deepgram, and Azure STT to prevent single-point failures.

When should I use a multi-provider API gateway for speech-to-text processing?▼

Use a multi-provider API gateway for speech-to-text processing when you need improved reliability and want to avoid managing individual STT provider integrations in production pipelines.

Related Skills

Explore More Software Engineering Skills→
moltis-orgmoltis-org
2.8k

openai-whisper-api

Transcribe audio files via OpenAI's Whisper API endpoint.

Official
Intermediate
maxgent-aimaxgent-ai

audio-transcribe

Transcribe audio and video files with word-level timestamps using WhisperX.

Official
Advanced
guoqiaoguoqiao

mlx-audio-server

Serve OpenAI-compatible audio APIs for speech-to-text and text-to-speech on Apple Silicon.

Community
Intermediate
astoreyaiastoreyai
3

stt-transcription

Transcribe audio from files or microphones using multiple speech-to-text engines.

Community
Advanced