Unfragile

The request names haoheliu/audio-ldm, an open-source text-to-audio model; none of the candidate sources describe that model directly. The closest matches are hosted platforms for audio generation and transcription, listed below as alternatives that do the same job (generating audio from text) in the form the sources show.

1
Replicate Google Lyria 2replicate.comverified and signed
Replicate runs open-source machine learning models through a cloud API 9, and its Lyria 2 model generates 48kHz stereo audio from text prompts 19.
Website Docs Pricing Get started
for agents: google/lyria-2
2
ElevenLabselevenlabs.iofound in code, not yet checked
ElevenLabs offers a voice generator and sound-effects generation from text descriptions via its APIs and SDKs 313.
Website Docs Pricing Get started
official:MCP server · ElevenLabs+45 community tools built for it
for agents: text_to_voice · text_to_sound_effects · sound-effects
3
Inference (inference.sh)inference.shverified and signed
Inference runs many AI models behind one API, including text-to-speech and text-to-sound-effects models, via its CLI 1020.
Website Docs Pricing Get started
for agents: elevenlabs-sound-effects · ai-voice-cloning · text-to-speech
4
OpenAI APIopenai.comverified and signed
The OpenAI API offers a Text-to-Speech action that turns text into a spoken audio file 11.
Website
official:API · OpenAI API SDK · openai library · OpenAI skill · babysit-pr SDK · openai+163 community tools built for it
for agents: text_to_speech · transcribe · createTranslation

Sources

3Free AI Voice Generator & Voice Agents Platform | ElevenLabselevenlabs.io · read 2026-10-29
9Replicate - Run AI with an APIreplicate.com · read 2026-10-29
10run any ai model with one api | inference shellinference.sh · read 2026-10-29
11OpenAI (Activepieces): declares "text_to_speech" (the record we read and signed)unfragile.ai · read 2026-10-24
13ElevenLabs MCP Server: declares "text_to_voice" (the record we read)github.com · read 2026-10-24
19google/lyria-2: declares "google/lyria-2" (the record we read and signed)unfragile.ai · read 2026-10-24
20elevenlabs-sound-effects: declares "elevenlabs-sound-effects" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

text_to_speech · OpenAI (Activepieces) verified and signed
Text-to-Speech — Turn text into a spoken audio file.
llm · mistral-vibe verified and signed
text_to_voice · ElevenLabs MCP Server found in code, not yet checked
create-llms · create-llms verified and signed
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
runway_generateAudio · Runway API MCP Server found in code, not yet checked
Generate spoken audio (text-to-speech) from text. Returns IMMEDIATELY with status PENDING and a taskId — does NOT wait for completion. Poll with runway_getTask(taskId) after ~15-30s; never re-submit on host timeouts. Default model is `seed_audio`; `eleven_multilingual_v2` requires a `voice`. Call ru
transcribe-audio · Groq (Activepieces) verified and signed
Transcribe Audio — Turn speech in an audio file into text, in the language spoken.
add-audio-track · Cloudflare API verified and signed
Add audio tracks to a video
text_to_audio · MiniMax MCP Server found in code, not yet checked
google/lyria-2 · google/lyria-2 verified and signed
Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts
stackadoc/stable-audio-open-1.0 · stackadoc/stable-audio-open-1.0 verified and signed
Stable Audio Open is an open-source model optimized for generating short audio samples, sound effects, and production elements using text prompts.

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.