Deepgram | Nova-3 | Speech to Text
Transcribe audio files to text using Deepgram Nova-3 with speaker diarization, punctuation, and smart formatting for 47+ languages.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "deepgram-nova-3-speech-to-text",
"version": "0.0.1",
"input": {
"media_url": "https://example.com/interview.mp3",
"model": "nova-3",
"language_code": "en",
"diarize": true,
"punctuate": true
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| diarize |
boolean |
true |
Identify different speakers in the audio. Each word includes speaker ID and confidence. |
| language_code |
string |
auto |
Language of the audio (BCP-47 code). auto: automatic detection. multi: multilingual. enum: auto, multi, tr, ur, en, nl, uk, es, ar, de, fr, it, ja, ko, pt, ru, zh, hi, and more |
| media_url |
string |
|
Audio file URL to transcribe. Supports mp3, wav, m4a, flac, ogg, webm, mp4. |
| model |
string |
nova-3 |
Deepgram speech recognition model. nova-3: latest, best accuracy. nova-2: previous generation. enum: nova-3, nova-2 |
| multichannel |
boolean |
false |
Transcribe each audio channel independently. Enable when each channel has a different speaker. |
| punctuate |
boolean |
true |
Add punctuation marks and capitalization to the transcript. |
| smart_format |
boolean |
true |
Auto-format currency amounts, phone numbers, email addresses, and dates. |
Examples
Basic English transcription:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "deepgram-nova-3-speech-to-text",
"version": "0.0.1",
"input": {
"media_url": "https://example.com/podcast-episode.mp3",
"model": "nova-3",
"language_code": "en",
"diarize": true
}
}'
Japanese audio with smart formatting:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "deepgram-nova-3-speech-to-text",
"version": "0.0.1",
"input": {
"media_url": "https://example.com/japanese-audio.wav",
"language_code": "ja",
"smart_format": true,
"punctuate": true
}
}'
Multi-channel call center recording:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "deepgram-nova-3-speech-to-text",
"version": "0.0.1",
"input": {
"media_url": "https://example.com/call-recording.wav",
"model": "nova-3",
"multichannel": true,
"diarize": true,
"smart_format": true
}
}'
Related Models
Documentation
1---2name: deepgram-nova-3-speech-to-text3description: Deepgram | Nova-3 | Speech to Text. Transcribe audio to text with speaker diarization and smart formatting. Triggers: transcribe, speech to text, stt, deepgram, nova, audio4---56# Deepgram | Nova-3 | Speech to Text78Transcribe audio files to text using Deepgram Nova-3 with speaker diarization, punctuation, and smart formatting for 47+ languages.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "deepgram-nova-3-speech-to-text",20 "version": "0.0.1",21 "input": {22 "media_url": "https://example.com/interview.mp3",23 "model": "nova-3",24 "language_code": "en",25 "diarize": true,26 "punctuate": true27 }28 }'29```3031## Parameters3233| Parameter | Type | Default | Description |34|-----------|------|---------|-------------|35| diarize | boolean | true | Identify different speakers in the audio. Each word includes speaker ID and confidence. |36| language_code | string | auto | Language of the audio (BCP-47 code). auto: automatic detection. multi: multilingual. enum: auto, multi, tr, ur, en, nl, uk, es, ar, de, fr, it, ja, ko, pt, ru, zh, hi, and more |37| media_url | string | | Audio file URL to transcribe. Supports mp3, wav, m4a, flac, ogg, webm, mp4. |38| model | string | nova-3 | Deepgram speech recognition model. nova-3: latest, best accuracy. nova-2: previous generation. enum: nova-3, nova-2 |39| multichannel | boolean | false | Transcribe each audio channel independently. Enable when each channel has a different speaker. |40| punctuate | boolean | true | Add punctuation marks and capitalization to the transcript. |41| smart_format | boolean | true | Auto-format currency amounts, phone numbers, email addresses, and dates. |4243## Examples4445**Basic English transcription:**46```bash47curl -X POST https://api.eachlabs.ai/v1/prediction \48 -H "Content-Type: application/json" \49 -H "X-API-Key: $EACHLABS_API_KEY" \50 -d '{51 "model": "deepgram-nova-3-speech-to-text",52 "version": "0.0.1",53 "input": {54 "media_url": "https://example.com/podcast-episode.mp3",55 "model": "nova-3",56 "language_code": "en",57 "diarize": true58 }59 }'60```6162**Japanese audio with smart formatting:**63```bash64curl -X POST https://api.eachlabs.ai/v1/prediction \65 -H "Content-Type: application/json" \66 -H "X-API-Key: $EACHLABS_API_KEY" \67 -d '{68 "model": "deepgram-nova-3-speech-to-text",69 "version": "0.0.1",70 "input": {71 "media_url": "https://example.com/japanese-audio.wav",72 "language_code": "ja",73 "smart_format": true,74 "punctuate": true75 }76 }'77```7879**Multi-channel call center recording:**80```bash81curl -X POST https://api.eachlabs.ai/v1/prediction \82 -H "Content-Type: application/json" \83 -H "X-API-Key: $EACHLABS_API_KEY" \84 -d '{85 "model": "deepgram-nova-3-speech-to-text",86 "version": "0.0.1",87 "input": {88 "media_url": "https://example.com/call-recording.wav",89 "model": "nova-3",90 "multichannel": true,91 "diarize": true,92 "smart_format": true93 }94 }'95```9697## Related Models9899- [deepgram-nova-3-speech-to-text-pro](../deepgram-nova-3-speech-to-text-pro/) - Pro version with sentiment, entities, intents, and summarization100- [elevenlabs-speech-to-text-scribe-v2](../elevenlabs-speech-to-text-scribe-v2/) - ElevenLabs speech to text101102## Documentation103104- [each::labs Docs](https://docs.eachlabs.ai)105- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia