Speech-to-Text Rest API

Synchronous Processing

Process short audio files with immediate response. Best for quick transcriptions and testing with a maximum duration of 30 seconds.

Saarika: Speech to Text Transcription Model

Saarika is a speech-to-text transcription model that excels in handling multi-speaker content, mixed language content, and conference recordings. It offers automatic code-mixing and enhanced multilingual support, making it ideal for a wide range of applications.

Code Examples for Speech to Text Transcription

1
from sarvamai import SarvamAI
2
3
client = SarvamAI(
4
    api_subscription_key="YOUR_SARVAM_API_KEY",
5
)
6
7
response = client.speech_to_text.transcribe(
8
    file=open("audio.wav", "rb"),
9
    model="saarika:v2.5",
10
    language_code="gu-IN"  # Or use "unknown" for automatic language detection
11
)
12
13
print(response)

Saaras Model: SOTA Speech to Text Translation Model

Saaras is a domain-aware translation model with enhanced telephony support and intelligent entity preservation. It is designed to handle complex language variations and domain-specific content, making it ideal for call center and telephony applications.

Code Examples for Speech to Text Translation

1
from sarvamai import SarvamAI
2
3
client = SarvamAI(
4
    api_subscription_key="YOUR_SARVAM_API_KEY",
5
)
6
7
response = client.speech_to_text.translate(
8
    file=open("audio.wav", "rb"),
9
    model="saaras:v2.5"
10
)
11
12
print(response)

API Response Format

Speech to Text Transcription Response

1
{
2
  "request_id": "20241115_12345678-1234-5678-1234-567812345678",
3
  "transcript": "नमस्ते, आप कैसे हैं?",
4
  "language_code": "hi-IN"
5
}

Speech to Text Translation Response

Supported source languages: hi-IN, bn-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN, gu-IN, en-IN

1
{
2
  "request_id": "20241115_12345678-1234-5678-1234-567812345678",
3
  "transcript": "Hello, how are you?",
4
  "language_code": "hi-IN"
5
}

Error Responses

All errors return a JSON object with an error field containing details about what went wrong.

Error Response Structure

1
{
2
  "error": {
3
    "message": "Human-readable error description",
4
    "code": "error_code_for_programmatic_handling",
5
    "request_id": "unique_request_identifier"
6
  }
7
}

Error Codes Reference

Example Error Response

1
{
2
  "error": {
3
    "message": "Unsupported audio format. Supported formats: WAV, MP3, AAC, FLAC, OGG",
4
    "code": "unprocessable_entity_error",
5
    "request_id": "20241115_abc12345"
6
  }
7
}

1
from sarvamai import SarvamAI
2
from sarvamai.core.api_error import ApiError
3
4
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5
6
try:
7
    response = client.speech_to_text.transcribe(
8
        file=open("audio.wav", "rb"),
9
        model="saarika:v2.5",
10
        language_code="hi-IN"
11
    )
12
    print(response.transcript)
13
except ApiError as e:
14
    if e.status_code == 400:
15
        print(f"Bad request: {e.body}")
16
    elif e.status_code == 403:
17
        print("Invalid API key. Check your credentials.")
18
    elif e.status_code == 429:
19
        print("Rate limit exceeded. Wait and retry.")
20
    elif e.status_code == 503:
21
        print("Service overloaded. Retry with backoff.")
22
    else:
23
        print(f"Error {e.status_code}: {e.body}")

Next Steps