XTTS-v2 is an open multilingual text-to-speech and voice cloning model, and it is available as a hosted action on Replicate, which offers a cloud API to run open-source models 1. Among the other sources, ElevenLabs offers text-to-speech and voice cloning through its own API and SDKs 7, and Hugging Face hosts many open speech models that can be run with its tooling 8.
- 1
Replicatereplicate.comverified and signed
Runs open-source models such as Coqui XTTS-v2 multilingual text-to-speech and voice cloning through a cloud API 1.
+14 community tools built for it
for agents: lucataco/xtts-v2 · x-lance/f5-tts · minimax/voice-cloning
- 2
ElevenLabselevenlabs.iofound in code, not yet checked
Creates lifelike speech and clones voices in 90+ languages through its voice AI platform and secure APIs and SDKs 7.
official:MCP server · ElevenLabsAPI · ElevenLabs API Documentation+59 community tools built for it
for agents: voice_clone · Text_to_speech_v1_text_to_speech__voice_id__post · text-to-speech
- 3
Hugging Facehuggingface.coverified and signed
Hosts open speech and audio models and lets you run them with its Transformers.js and hub tooling 8.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: train-sentence-transformers · text_classification · transformers-js
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 7Free AI Voice Generator & Voice Agents Platform | ElevenLabselevenlabs.io · read 2026-10-29
- 8Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
For agents: the 10 actions behind this answer
lucataco/xtts-v2 · lucataco/xtts-v2 verified and signed
Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning
text_to_speech · OpenAI (Activepieces) verified and signed
Text-to-Speech — Turn text into a spoken audio file.
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
text-to-speech · TTS FastPitch HifiGAN Riva verified and signed
Task: Text to Speech
ts · microsoft-cognitiveservices-speech-sdk verified and signed
HuggingFace · sagemaker verified and signed
voice_clone · ElevenLabs MCP Server found in code, not yet checked
train-sentence-transformers · train-sentence-transformers verified and signed
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification
workers-ai-search-model · Cloudflare API verified and signed
Model Search
add · gpt-rag-mcp found in code, not yet checked
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.