Hugging Face Audio AI
Pricing
from $0.01 / 1,000 results
Hugging Face Audio AI
Audio w/Hugging Face models speech recognition, text-to-speech & audio analysis Speech-to-Text: Transcribe audio Text-to-Speech: Generate natural speech Audio Classification: Classify sounds Voice Activity Detection: Detect speech Speaker Diarization: Identify speakers Music Generation: Create music
Pricing
from $0.01 / 1,000 results
Rating
0.0
(0)
Developer
The Howlers
Maintained by CommunityActor stats
0
Bookmarked
28
Total users
1
Monthly active users
17 hours ago
Last modified
Categories
Share
Hugging Face Audio
Audio processing with Hugging Face - speech recognition, text-to-speech, audio classification, and voice cloning.
BYOK (Bring Your Own Key) -- you provide your own API credentials.
Before You Start
This actor requires your own API credentials to fetch real data.
Where to get your key: Your Hugging Face API token
Demo Mode is off by default, so runs fetch real data. Set demoMode to true to get free sample data that shows the output format, no key needed.
Quick Start
Test with Demo Mode (free, no API key needed)
Run with real data
Input Parameters
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
task | string | "speech_to_text" | Yes* | The audio operation to perform |
apiToken | string | - | Yes* | Your Hugging Face API token |
model | string | - | No | Hugging Face model ID (leave blank for default) |
audioUrl | string | - | No | URL of input audio file |
text | string | - | No | Text to convert to speech |
language | string | "en" | No | Language code (e.g., en, es, fr, de) |
targetLanguage | string | - | No | Target language for translation |
voicePreset | string | "default" | No | Voice style for TTS |
speakerId | integer | - | No | Speaker voice ID for multi-speaker models |
musicPrompt | string | - | No | Text description for music generation |
duration | number | 10 | No | Duration of generated audio |
sampleRate | integer | 22050 | No | Audio sample rate in Hz |
returnTimestamps | boolean | false | No | Include word-level timestamps in transcription |
waitForModel | boolean | true | No | Wait for model to load if not ready |
webhookUrl | string | - | No | URL to receive results via webhook |
demoMode | boolean | false | No | Run with sample data (no API calls) |
*Required when Demo Mode is off.
Pricing
This actor uses pay-per-event billing:
| Event | When it is charged | Price |
|---|---|---|
| Actor start | Once when the run starts, one event per GB of memory (minimum one). At the default 4 GB of memory a run starts at $0.40 | $0.10 per GB |
| Speech to Text | Transcribe audio to text using Whisper large-v3 | $0.01 |
| Text to Speech | Generate natural speech from text input | $0.01 |
| Audio Classification | Classify sounds, music, speech, and environmental audio | $0.01 |
| Audio Enhancement | Audio source separation and noise reduction | $0.01 |
| Voice Activity Detection | Detect speech segments in audio files | $0.01 |
| Speaker Diarization | Identify and separate different speakers in audio | $0.01 |
| Audio Embeddings | Generate vector embeddings for audio similarity | $0.01 |
| Music Generation | Generate music from text descriptions using MusicGen | $0.01 |
| Result | Each item written to the default dataset | $0.00001 |
Demo mode is free -- no charges for sample data.
Troubleshooting
"API key is required"
You have Demo Mode turned off but didn't provide an API key. Either:
- Turn Demo Mode on to test with sample data
- Add your API key in the input
"API error 403" or "Unauthorized"
Your API key is invalid, expired, or doesn't have access to this specific API endpoint. Double-check your key and account permissions.
"API error 429" or "Rate limit"
Too many requests. Wait a minute and try again, or reduce the number of items per run.
No results or empty dataset
Check the run log for error messages. Common causes:
- Invalid input format (check the examples above)
- API key without proper permissions
- The target data doesn't exist or is too small to track
How do I test without an API key?
Enable Demo Mode in the input. This returns realistic sample data so you can verify the output format works for your workflow.
Built by John Rippy | Actor Arsenal
