Unfragile

The request names StyleTTS 2, which is an open-source text-to-speech model. Replicate hosts it as the adirik/styletts2 model, callable through its API 111. Other products listed here offer speech generation, but none of their sources name StyleTTS 2 specifically.

1
Replicate Adirik Styletts2replicate.comverified and signed
Hosts the adirik/styletts2 model, which generates speech from text, callable through the Replicate cloud API 111.
Website Docs Pricing Get started
for agents: adirik/styletts2
2
LocalAIlocalai.ioverified and signed
Open-source engine that runs voice models such as text-to-speech on local hardware through one runtime 919.
Website Docs
+5 community tools built for it
for agents: text_to_speech · transcribe_audio · create_embedding
3
rhapsoderhapsode.devwebsite read, tools not yet checked
Self-hosted multi-engine speech server that exposes many TTS models behind one HTTP API, so a TTS engine can be installed and called locally 10.
Website Docs
4
ElevenLabselevenlabs.ioverified and signed
Commercial AI voice generator with a text-to-speech action and an MCP server for generating speech from text 717.
Website Docs Pricing Get started
official:MCP server · ElevenLabs+45 community tools built for it
for agents: elevenlabs-text-to-speech · text-to-speech · text_to_speech

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
9LocalAI · Make AI run on every machinelocalai.io · read 2026-10-29
10rhapsoderhapsode.dev · read 2026-10-30
11adirik/styletts2: declares "adirik/styletts2" (the record we read and signed)unfragile.ai · read 2026-10-24
17ElevenLabs (Activepieces): declares "elevenlabs-text-to-speech" (the record we read and signed)unfragile.ai · read 2026-10-24
19LocalAI (Activepieces): declares "text_to_speech" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

adirik/styletts2 · adirik/styletts2 verified and signed
Generates speech from text
jaaari/kokoro-82m · jaaari/kokoro-82m verified and signed
Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)
alphanumericuser/kokoro-82m · alphanumericuser/kokoro-82m verified and signed
Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)
vladpolbennikov/kokoro-82m-all-voices · vladpolbennikov/kokoro-82m-all-voices verified and signed
Kokoro v1.0 2025 Jan 27 - text-to-speech (82M params, based on StyleTTS2)
finnish-humanizer · finnish-humanizer verified and signed
Detect and remove AI-generated markers from Finnish text, making it sound like a native Finnish speaker wrote it. Use when asked to "humanize", "naturalize", or "remove AI feel" from Finnish text, or when editing .md/.txt files containing Finnish content. Identifies 26 patterns (12 Finnish-specific
llm · mistral-vibe verified and signed
lucataco/xtts-v2 · lucataco/xtts-v2 verified and signed
Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning
analyze-test-run · analyze-test-run verified and signed
analyze-test-run — an installable skill for AI agents.
text_to_speech · OpenAI (Activepieces) verified and signed
Text-to-Speech — Turn text into a spoken audio file.
stream-subtitles/-captions-generate-caption-or-subtitle-for-language · Cloudflare API verified and signed
Generate captions or subtitles for a provided language via AI

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.