Route text-to-speech requests through OmniRoute to generate spoken audio.
npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-tts
Please help me install this Agent Skill. Skill: omniroute-tts Source: https://github.com/diegosouzapw/OmniRoute/tree/main/skills/omniroute-tts Command: npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-tts
OmniRoute TTS removes the hassle of picking the “right” text-to-speech provider by automatically routing a single request to a provider that can fulfill it, producing spoken audio output reliably.
/v1/audio/speech API./v1/models/tts to discover supported voices per provider and select the best one.Use case: Generate spoken narration for a chatbot response, tutorial script, or app notification while minimizing voice/provider failures and keeping output consistent.
Send a POST request to $OMNIROUTE_URL/v1/audio/speech with Authorization: Bearer $OMNIROUTE_KEY and a JSON body specifying model: "tts-1", your input text, a supported voice name (check /v1/models/tts), and your response_format (such as mp3).
High-intent search queries and answers about installing and using this skill.
Text-to-speech fallback routing automatically retries your audio generation request across different AI providers like OpenAI, ElevenLabs, Azure, and Google Cloud if the initial provider fails, ensuring reliable spoken audio output.
To generate spoken audio, send a POST request to the /v1/audio/speech endpoint with your text input, a TTS model like tts-1, a supported voice, and the desired response format such as mp3 to receive an audio binary.
Yes, you need an OMNIROUTE_URL and OMNIROUTE_KEY to authenticate audio generation requests using Bearer authorization when sending text-to-speech requests through the OmniRoute API.
You can discover supported voices per provider by querying the /v1/models/tts endpoint, allowing you to select the best available voice for your text-to-speech audio generation needs.
Yes, you can specify mp3 as your response_format in the JSON body of your text-to-speech request to receive audio binaries in mp3 format from the provider.
The best way to avoid provider failures during voice generation is to use a unified TTS endpoint with auto-fallback routing, which automatically switches to alternative AI providers if the primary one fails.
diegosouzapwProvides speech-to-text transcription and translation via OmniRoute-compatible endpoints with provider auto-fallback.
bibo1243Convert text to an MP3 audio file and return its file path.
BEIRUXGenerate ElevenLabs text-to-speech audio and play it locally via CLI.
jholhewresConvert text to speech and manipulate audio via APIs and command-line tools.