@radzor/text-to-speech

Text-to-speech synthesis using OpenAI TTS or ElevenLabs. Produces audio from text with configurable voice, speed, and output format.

AI & MLv0.1.0typescriptpythonServerttsspeechvoiceelevenlabsopenaiaudiosynthesisby Radzor

Install

View source on GitHub →

$npx radzor@latest add text-to-speech

⚠ Constraints: Requires API key. OpenAI TTS input limit is 4096 characters per request. Server-side only.

Inputs

Name	Type	Default	Description
provider*	'openai' \| 'elevenlabs'	—	TTS provider to use.
apiKey*	string	—	API key for the selected provider.OPENAI_API_KEY
voice	string	alloy	Voice ID or name (e.g. alloy, echo, shimmer for OpenAI).
model	string	—	Model identifier (e.g. tts-1, tts-1-hd, eleven_multilingual_v2).
speed	number	1	Speech speed multiplier (0.25 to 4.0 for OpenAI).

provider*'openai' | 'elevenlabs'

{ "llm": { "constraints": "Requires API key. OpenAI TTS input limit is 4096 characters per request. Server-side only.", "usageExamples": "llm/examples.md", "integrationPrompt": "llm/integration.md" }, "name": "@radzor/text-to-speech", "tags": [ "tts", "speech", "voice", "elevenlabs", "openai", "audio", "synthesis" ], "events": [ { "name": "onSynthesized", "payload": { "size": "number", "voice": "string", "format": "string" }, "description": "Fired when audio synthesis is complete." }, { "name": "onError", "payload": { "code": "string", "message": "string" }, "description": "Fired when synthesis fails." } ], "inputs": [ { "name": "provider", "type": "'openai' | 'elevenlabs'", "required": true, "description": "TTS provider to use." }, { "name": "apiKey", "type": "string", "envVar": "OPENAI_API_KEY", "required": true, "description": "API key for the selected provider." }, { "name": "voice", "type": "string", "default": "alloy", "required": false, "description": "Voice ID or name (e.g. alloy, echo, shimmer for OpenAI)." }, { "name": "model", "type": "string", "required": false, "description": "Model identifier (e.g. tts-1, tts-1-hd, eleven_multilingual_v2)." }, { "name": "speed", "type": "number", "default": 1, "required": false, "description": "Speech speed multiplier (0.25 to 4.0 for OpenAI)." } ], "radzor": "1.0.0", "actions": [ { "name": "synthesize", "params": [ { "name": "text", "type": "string", "description": "Text to convert to speech." }, { "name": "options", "type": "SynthesizeOptions", "description": "Optional overrides for voice, speed, format." } ], "returns": "Promise<Buffer>", "description": "Convert text to speech audio." }, { "name": "synthesizeToFile", "params": [ { "name": "text", "type": "string", "description": "Text to convert." }, { "name": "outputPath", "type": "string", "description": "File path to save audio." } ], "returns": "Promise<void>", "description": "Convert text to speech and save to a file." } ], "outputs": [ { "name": "audioData", "type": "Buffer", "description": "Generated audio data as a buffer." } ], "runtime": "server", "version": "0.1.0", "category": "ai", "languages": [ "typescript", "python" ], "description": "Text-to-speech synthesis using OpenAI TTS or ElevenLabs. Produces audio from text with configurable voice, speed, and output format.", "dependencies": { "radzor": [], "packages": {} }, "composability": { "connectsTo": [ { "output": "audioData", "compatibleWith": [ "@radzor/file-upload.action.upload.data" ] } ] } }

@radzor/text-to-speech

Install

Inputs

Outputs

Actions

Events

Composability

radzor.manifest.json

Version History