Audio & Voice Generation

Generate music and sound effects from text, and synthesize speech (text-to-speech), on the generative backend.

Active public models

Text-to-audio (music / sound):

Model	Endpoint	Source repo
MusicGen Small	hf-facebook-musicgen-small	facebook/musicgen-small
AudioLDM2	hf-cvssp-audioldm2	cvssp/audioldm2

Text-to-speech (voice):

Model	Endpoint	Source repo
Chatterbox	chatterbox-tts	ResembleAI/chatterbox-turbo
Kokoro 82M	kokoro-tts	hexgrad/Kokoro-82M
Bark Small	hf-suno-bark-small	suno/bark-small
Parler-TTS Mini	hf-parler-tts-parler-tts-mini-v1	parler-tts/parler-tts-mini-v1

All active endpoints are currently free; several are candidate. Verify in the live catalog:

curl "https://api.colabhive.com/api/builder/v1/endpoints?visibility=public&task_type=text-to-speech"
curl "https://api.colabhive.com/api/builder/v1/endpoints?visibility=public&task_type=text-to-audio"

You can import HuggingFace audio models as well.

Quick start

Text-to-music

from colabhive import ColabHive

client = ColabHive(api_key="hive_...", account_id="YOUR_ACCOUNT_ID")

result = client.endpoints.infer(
    endpoint_id="hf-facebook-musicgen-small",   # SDK resolves the name to a UUID
    input_data={"prompt": "Upbeat jazz piano melody with drums", "duration_s": 15},
)
for art in result.get("result", {}).get("output_artifacts", []):
    client.endpoints.download_artifact(art["url"], f"./{art['filename']}")

Text-to-speech

result = client.endpoints.infer(
    endpoint_id="kokoro-tts",
    input_data={"text": "Welcome to ColabHive, the distributed AI platform.", "voice": "af_heart"},
)

Input parameters

text-to-audio

Parameter	Type	Default	Description
prompt	string	required	Description of the audio/music
duration_s	number	10.0	Duration in seconds

text-to-speech

Parameter	Type	Default	Description
text	string	required	Text to speak
voice / voice_preset	string	model-specific	Voice identity (e.g. Kokoro af_heart, Bark v2/en_speaker_6)

Output format

{
  "output_artifacts": [
    {
      "filename": "audio.wav",
      "url": "https://storage.colabhive.com/...",
      "content_type": "audio/wav",
      "size_bytes": 640000,
      "modality": "audio"
    }
  ],
  "metadata": { "duration_s": 15.0 }
}

Related

• Generative Models · Image · Video
• Inference API

---

Authors: José Luis Minich, Maximiliano Lucius.