SpeechBrain
SpeechBrain is a comprehensive open-source Python/torch SDK offering speech‑to‑text, speaker ID, speech enhancement, separation, TTS, diarization, and more. With extensive docs, Hugging Face inference API, and active GitHub, it’s ideal for building speech‑powered apps and research.
1
Endpoints
27
Views
Jul 20, 2025
Last Checked
NaN
Rate Limit
API Endpoints
Transcribes audio to text using ASR models
Full URL
https://api.speechbrain.io/v1/asrCode Examples
curl -X POST 'https://api.speechbrain.io/v1/asr' \
-H 'Authorization: Bearer YOUR_API_KEY'Parameters
{
"audio": "base64_audio_data",
"language": "en-US"
}Example Response
{
"text": "Hello world this is a test",
"language": "en-US",
"confidence": 0.89
}Version
v1
Rate Limit
100 minutes/day
Tags
asrspeech-processing
Technical Details
Authentication
NoneResponse Formats
JSONAvailability
globalStatus
Published Rate Limits
Self-hosted
Supported Languages
Python
Use Cases
voice assistants
transcription
Related APIs
Discover similar APIs that might interest you