Speech Synthesis
Select a voice and type your text to generate speech. Powered by OmniVoice.
🎤
No voice selected
Click to select or add a voice
That's a long passage. Split it into segments for better quality output.
Inference Steps
32
Speed
1.0x
Generated audio
Voice Design
Describe how you want the voice to sound. Powered by Qwen3-TTS.
Voice Description
Generated audio
Voice Changer
Transform speech into any target voice. Powered by Seed-VC.
Source audio
Drop source audio or click to upload
The speech you want to convert
Target voice
Drop target voice or click to upload
Short clip of the voice to convert to
Diffusion Steps
10
Similarity
0.7
Converted audio
Voice Cleaner
Strip background noise from speech and optionally restore clarity. Powered by Resemble Enhance.
Drop noisy audio or click to upload
MP3, WAV, FLAC, M4A · speech with background noise
NFE Steps
64
Prior Tau
0.5
Enhanced audio
Sound Effects
Generate sound effects from a text prompt. Powered by Stable Audio 3.
Duration
5s
Inference Steps
8
Generated sound
Voice Library
Preset speakers and your custom cloned voices. Select one to use in Voice Generation.
Your Voices
Preset Speakers
Transcribe
Upload an audio file to transcribe it to text. Powered by Cohere Transcribe.
Drop an audio file here or click to upload
MP3, WAV, FLAC, M4A supported
History
Your recent generations.
No generations yet
API
Call any of these features directly from your code or AI agent using your HF token.
Use with AI agents — These API calls work great with Claude Code, Cursor, Windsurf, or any AI coding agent. Paste a snippet into your agent's context and ask it to call the feature. The agent can use your
HF_TOKEN environment variable to authenticate. Works with MCP servers, automation scripts, and CI/CD pipelines too.