9router-stt
9router-stt converts speech to text by routing requests through 9Router's unified /v1/audio/transcriptions endpoint, supporting multiple STT providers including OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, and HuggingFace. Configure your model choice, audio file, and optional parameters like language, prompt, and response format (json, text, verbose_json, srt, or vtt) to get transcriptions with timestamps or subtitles.
9router-stt transcribes audio files to text using OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, or HuggingFace models.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-20
9router-stt transcribes audio files to text using OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, or HuggingFace models. 9router-stt converts speech to text by routing requests through 9Router's unified /v1/audio/transcriptions endpoint, supporting multiple STT providers including OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, and HuggingFace. Configure your model choice, audio file, and optional parameters like language, prompt, and response format (json, text, verbose_json, srt, or vtt) to get transcriptions with timestamps or subtitles.
Use it when
- 9router-stt transcribes audio files by accepting your audio input (MP3, WAV, M4A, etc.) along with your chosen model provider.
- 9router-stt supports five response formats: json (default), text (plain transcription), verbose_json (with metadata).
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
decolua/9router/9router-stt · repository language: JavaScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can 9router-stt do with audio files?
9router-stt converts speech to text by routing transcription requests through 9Router's unified /v1/audio/transcriptions endpoint. It supports multiple STT providers including OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, and HuggingFace, allowing you to transcribe audio files and generate subtitles in SRT or VTT format with timestamps.
How do I transcribe audio files using 9router-stt?
9router-stt transcribes audio files by accepting your audio input (MP3, WAV, M4A, etc.) along with your chosen model provider. Configure optional parameters like language, prompt, and response format, then submit to the /v1/audio/transcriptions endpoint. The skill returns text transcriptions with timestamps and segment details based on your selected format.
What response formats does 9router-stt support?
9router-stt supports five response formats: json (default), text (plain transcription), verbose_json (with metadata), srt (SubRip subtitle format), and vtt (WebVTT subtitle format). Choose your format based on whether you need timestamps, segment details, or subtitle files for video integration.
Can 9router-stt transcribe audio with timestamps?
Yes, 9router-stt extracts text from audio with timestamps and segment details when you use json, verbose_json, srt, or vtt response formats. These formats preserve timing information, making it easy to sync transcriptions with video or generate subtitle files for multimedia content.
Which STT providers does 9router-stt route to?
9router-stt routes transcription requests across multiple providers: OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI, NVIDIA, and HuggingFace. You select your preferred provider when making a request, giving you flexibility to choose based on speed, accuracy, cost, or language support needs.
Does 9router-stt support multiple languages?
Yes, 9router-stt supports transcription in multiple languages. You can specify the language parameter when submitting your audio file, and the skill will route your request to the appropriate STT provider configured for that language, ensuring accurate transcription across different linguistic content.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
9Router — Speech-to-Text
Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.
Discover
curl $NINEROUTER_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$NINEROUTER_URL/v1/models/info?id=openai/whisper-1"
model = STT model ID (e.g. openai/whisper-1, groq/whisper-large-v3, deepgram/nova-3, gemini/gemini-2.5-flash).
Endpoint
POST $NINEROUTER_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)
| Field | Required | Notes |
|---|---|---|
model |
yes | from /v1/models/stt |
file |
yes | audio file (mp3, wav, m4a, webm, ogg, flac) |
language |
no | ISO-639-1 (e.g. en, vi) |
prompt |
no | hint text to guide transcription |
(truncated - see the full file via the links below)
File tree — 1 file
skills/9router-stt/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Transcribe audio files to text using multiple STT providers”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
9router-tts routes text-to-speech requests to your choice of seven major providers—OpenAI, ElevenLabs, Deepgram, Edge TTS, Google TTS, Hyperbolic, and Inworld—through a unified API endpoint. Query available models and voices per provider, then POST your text with a voice ID to receive MP3 audio or base64-encoded JSON. Each provider has its own authentication and voice naming scheme, all abstracted behind a single interface.
9router-chat lets you send chat and code generation requests through 9Router's multi-provider routing layer, supporting both OpenAI and Anthropic API formats with streaming enabled. Built-in fallback combos automatically switch between providers, letting you discover available models and their capabilities on demand.
This skill routes web content extraction through multiple providers—Firecrawl, Jina Reader, Tavily, and Exa—returning structured markdown, text, or HTML output. Configure your preferred provider or use auto-fallback chaining to ensure reliable scraping and article parsing.
Access vector embeddings through a unified 9Router endpoint supporting OpenAI, Gemini, Mistral, Voyage, Nvidia, GitHub, and other embedding models. Configure your preferred provider and send text to receive embeddings in standard OpenAI format, with optional base64 encoding and dimension control for compatible models.
Turn podcasts, interviews, and videos into searchable text using OpenAI's Whisper model. Choose from multiple output formats—plain text, SRT subtitles, JSON, and more—with adjustable accuracy levels to match your needs. Handles batch processing and automatic language detection.
Whisper is OpenAI's multilingual automatic speech recognition model, trained on 680,000 hours of audio data. It handles transcription, translation to English, and language identification across 99 languages with six configurable model sizes ranging from 39M to 1550M parameters. Use it for podcast transcription, meeting notes, noisy audio processing, or any speech-to-text task requiring robust multilingual support.