Batch Speech-to-Text API

Process long audio files (up to 1 hour) using synchronous or asynchronous methods. Ideal for meetings, interviews, call center recordings, and large-scale content processing pipelines.

Supports files up to 1 hour long
Advanced transcription and translation
Speaker diarization and timestamp support

Note: You can upload up to 20 audio files per job.

Features

Processing

Supports up to 1 hour audio
Synchronous and asynchronous job-based API
Upload multiple files per job

Audio & Language Support

Indian languages and English - Automatic language detection - Diarization and timestamp support

Timestamps

Chunk-level timestamp support - Useful for subtitle alignment and audio navigation - Provides start and end times for each segment of text

Speaker Diarization

Identify multiple speakers
Output includes speaker labels (SPEAKER_00, etc.)
Ideal for meetings and interviews

The SarvamAI SDK supports both synchronous and asynchronous programming in Python. This refers to how your code interacts with the SDK, not how the server handles the processing of requests.

Code Examples

Saarika Model: Batch Speech-to-Text Transcription

Synchronous (Python)

Asynchronous (Python)

JavaScript

1 from sarvamai import SarvamAI
2 
3 def main():
4 client = SarvamAI(api_subscription_key="YOUR_API_KEY")
5 
6     job = client.speech_to_text_job.create_job(
7         language_code="en-IN",
8         model="saarika:v2.5",
9         with_timestamps=True,
10         with_diarization=True,
11         num_speakers=2
12     )
13 
14     audio_paths = ["path/to/audio.mp3"]
15     job.upload_files(file_paths=audio_paths)
16 
17     job.start()
18 
19     final_status = job.wait_until_complete()
20 
21     if job.is_failed():
22         print("STT job failed.")
23         return
24     output_dir = "./output"
25     job.download_outputs(output_dir=output_dir)
26     print(f"Output downloaded to: {output_dir}")
27 
28 if __name__ == "__main__":
29 main()
30 
31 # --- Notebook/Colab usage ---
32 
33 #main()

Saaras Model: Batch Speech-to-Text Translation

Synchronous (Python)

Asynchronous (Python)

JavaScript

1 from sarvamai import SarvamAI
2 
3 def main():
4     client = SarvamAI(api_subscription_key="YOUR_API_KEY")
5 
6     job = client.speech_to_text_translate_job.create_job(
7         model="saaras:v2.5",
8         with_diarization=True,
9         num_speakers=2,
10         prompt="Official meeting"
11     )
12 
13     audio_paths = ["path/to/audio.mp3"]
14     job.upload_files(file_paths=audio_paths)
15 
16     job.start()
17 
18     final_status = job.wait_until_complete()
19 
20     if job.is_failed():
21         print("STT job failed.")
22         return
23 
24     output_dir = "./output"
25     job.download_outputs(output_dir=output_dir)
26     print(f"Output downloaded to: {output_dir}")
27 
28 if __name__ == "__main__":
29     main()
30 
31 # --- Notebook/Colab usage ---
32 #main()

Next Steps

Choose Your API

Select the appropriate API type based on your use case.

Get API Key

Go Live

Deploy your integration and monitor usage in the dashboard.

Need help choosing the right API? Contact us on discord for guidance.