Speech to Text API
Accurate Transcription at Low Cost
Transcribe audio files to text with high accuracy. 28+ languages, timestamps, auto-detection. Starting at $2 for 100K credits. No subscription.
28+
Languages
High
Accuracy
Auto
Language detect
Timestamps
Word-level
Code Examples
Upload audio, receive transcribed text in JSON.
import requests
with open("audio.mp3", "rb") as f:
response = requests.post(
"https://cheapaiapi.com/api/v1/speech-to-text",
headers={"Authorization": "Bearer sk_your_api_key"},
files={"audio": f},
data={
"language": "en", # Optional — auto-detect if omitted
"model": "whisper-1",
"response_format": "json"
}
)
result = response.json()
print(result["text"])
# "Hello, this is the transcribed content of the audio file."const formData = new FormData();
formData.append("audio", audioFile);
formData.append("language", "en");
formData.append("response_format", "json");
const response = await fetch(
"https://cheapaiapi.com/api/v1/speech-to-text",
{
method: "POST",
headers: { "Authorization": "Bearer sk_your_api_key" },
body: formData,
}
);
const { text, segments } = await response.json();
console.log(text); // Full transcription
// segments: timestamped word/sentence-level dataFeatures
28+ Languages
Transcribe audio in English, Spanish, French, Chinese, Arabic, Hindi, and 22+ more languages.
Word Timestamps
Get word-level or sentence-level timestamps with verbose_json response format.
Auto Language Detection
Omit the language parameter and the API will detect it automatically.
Multiple Formats
Receive output as plain text, JSON, SRT subtitles, or VTT captions.
Noise Tolerance
Works with real-world audio including mild background noise and accented speech.
Low Cost
Much cheaper than comparable transcription APIs with no accuracy trade-off.
Supported Languages
28+ languages with automatic detection.
Use Cases
Subtitles & Captions
Auto-generate SRT or VTT captions for videos with accurate timestamps.
Meeting Transcription
Transcribe calls and meetings to searchable text records automatically.
Podcast Transcripts
Convert podcast episodes into blog posts and SEO-friendly transcripts.
Voice Commands
Build voice-controlled interfaces with real-time audio transcription.
Content Repurposing
Transform audio interviews into written articles and social media copy.
Accessibility
Make audio and video content accessible for hearing-impaired audiences.
Frequently Asked Questions
How accurate is the transcription?expand_more
What audio formats are supported?expand_more
Does the API support timestamps?expand_more
Can the API auto-detect the spoken language?expand_more
Is there speaker diarization (who said what)?expand_more
How much does transcription cost?expand_more
Start Transcribing Today
Accurate audio-to-text transcription at a fraction of the cost. Pay only for what you use.
rocket_launchGet Started — $2 for 100K Credits