{"$schema":"https://app.monad.xyz/agents/api-hub/schema.json#/$defs/serviceArtifact","slug":"elevenlabs","name":"ElevenLabs","summary":"TTS / STT / music / SFX.","categories":["Media"],"status":"active","serviceUrl":"https://app.monad.xyz/agents/api-hub/elevenlabs.json","detailUrl":"https://app.monad.xyz/agents/api-hub/elevenlabs","catalogs":[{"slug":"monid","name":"Monid","url":"https://monid.ai","baseUrl":"https://x402.monid.ai/v1/run","manifestUrl":"https://api.monid.ai/public/v1/endpoints?provider=elevenlabs","endpoints":[{"method":"POST","path":"/v1/audio-isolation","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/audio-isolation"},"description":"Remove background noise, music and ambient sounds from a recording, returning clean studio-quality speech (MP3, base64).","priceUsd":0.12,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/v1/speech-to-speech","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/speech-to-speech"},"description":"Transform a recording into a different ElevenLabs voice while preserving the original emotion, timing and delivery (MP3, base64 output).","priceUsd":0.12,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/v1/forced-alignment","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/forced-alignment"},"description":"Align a known transcript to its audio recording, returning precise word-level timestamps (subtitles, audiobook timings, karaoke).","priceUsd":0.22,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"GET","path":"/voices","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/voices"},"description":"List the ElevenLabs voices available to this account (voice_id, name, category, labels, preview_url).","priceUsd":0,"pricing":{"model":"PER_CALL","unit":null}},{"method":"POST","path":"/v1/speech-to-text","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/speech-to-text"},"description":"Transcribe an audio or video file from a URL with ElevenLabs Scribe — 90+ languages, word timestamps, speaker diarization, audio-event tagging, optional entity detection and keyterm biasing.","priceUsd":0.22,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/v1/music","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/music"},"description":"Generate studio-grade music (MP3) in any style from a natural language prompt with Eleven Music — vocals or instrumental, commercial-use cleared.","priceUsd":0.15,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/v1/text-to-dialogue","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/text-to-dialogue"},"description":"Generate immersive multi-speaker dialogue audio (MP3) from text + voice_id pairs with ElevenLabs eleven_v3.","priceUsd":0.1,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/text-to-speech","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/text-to-speech"},"description":"Convert text to lifelike speech audio (MP3) with an ElevenLabs voice.","priceUsd":0.05,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}},{"method":"POST","path":"/v1/sound-generation","url":"https://x402.monid.ai/v1/run","body":{"provider":"elevenlabs","endpoint":"/v1/sound-generation"},"description":"Generate a high-quality sound effect (MP3) from a text description — cinematic hits, Foley, ambience, loops, musical elements.","priceUsd":0.12,"pricing":{"model":"PER_UNIT_MATRIX","unit":null}}]}],"payment":{"chain":"eip155:143","assets":["USDC"],"x402":"v2"},"listedAt":"2026-08-12","verifiedAt":"2026-08-12"}