Modulate
Modulate · Real-Time Transcription API

Transcription for Real-World Audio. #1 on Hugging Face.

Stop overpaying for transcription that breaks on messy audio. Modulate's transcription API delivers up to 10x better cost performance and was built to understand real conversations, not just studio recordings.

"This transcription model might be the best stuff I've seen. I've never seen another model with realtime diarization (that works?!)"
NL
Nick Leonard
CEO, VoiceRun
Free tier · no card needed
Get immediate API access
400 hours free. Start transcribing in minutes.
400 hours free · $0.03/hr after
independent benchmarks

Where accuracy meets cost.

Tested on Earnings-22 and VoxPopuli, two of the industry's most widely used accuracy benchmarks. Modulate's transcription API achieves the lowest Word Error Rate (WER) at the lowest price per hour in the market

Transcription Benchmark (Accuracy vs. Price)
Average Word Error Rate (WER) across Earnings-22 and VoxPopuli datasets
Lowest WER lowest cost
Cost per hour
Avg. Word Error Rate
modulate-transcribe
scribe-v2
assemblyai-universal-2
assemblyai-universal-3-pro
speechmatics-enhanced
google-gemini-2.5-pro
gpt-4o-transcribe
google-chirp-2
deepgram-nova-3
openai-whisper-large-v3
8
9
10
11
12
13 %
$0.00
0.10
0.20
0.30
$0.40
Speech-to-text api Capabilties

One API. Real-time transcription & enrichment.

Batch and real-time streaming available on the same API key. Capabilities that usually require separate models are built in and optional to turn on. No extra cost.

✓
Real-time diarization - Get speaker-separated transcripts out of the box
✓
70+ languages and dialects supported.
✓
Emotion and accent detection - 20+ emotions, 20+ accents, direct from audio
✓
PII/PHI tagging included. No add-on or post-processing step.
✓
REST batch and WebSocket streaming - same key, same endpoint pattern
Explore the docs →
bash
curl --request POST \
  --url https://platform.modulate.ai/api/velma-2-stt-batch \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-Key: <api-key>' \
  --form upload_file='@example-file' \
  --form speaker_diarization=true \
  --form emotion_signal=false \
  --form accent_signal=false \
  --form deepfake_signal=false \
  --form pii_phi_tagging=false
200 OK
JSON response
312ms
{
  "text": "Hello, how are you? Bonjour, ça va?",
  "duration_ms": 5000,
  "utterances": [
    {
      "utterance_uuid": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "text": "Hello, how are you?",
      "start_ms": 0,
      "duration_ms": 2000,
      "speaker": 1,
      "language": "en",
      "emotion": "Neutral",
      "accent": "American",
      "deepfake_score": null
    },
    {
      "utterance_uuid": "f6a7b8c9-d0e1-2345-fabc-456789012345",
      "text": "Bonjour, ça va?",
      "start_ms": 2500,
      "duration_ms": 2500,
      "speaker": 2,
      "language": "fr",
      "emotion": "Happy",
      "accent": "British",
      "deepfake_score": null
    }
  ]
}
Modulate transcription pricing

Transparent. On-demand. No lock-in.

No contracts, no volume minimums. Pay only for what you process.

Batch · REST APIUSD / hour processed
Modulate lowest cost
modulate-transcribe
$0.03
xAI
grok-stt
$0.10
AssemblyAI
universal-3 Pro
$0.21
ElevenLabs
scribe v2
$0.22
Deepgram
nova-3
$0.31
OpenAI
gpt-4o-transcribe
$0.36
Streaming · WebSocketUSD / hour live audio
Modulate lowest cost
modulate-transcribe
$0.06
xAI
grok
$0.20
Speechmatics
enhanced
$0.24
Deepgram
nova-3
$0.35
OpenAI
gpt-4o-transcribe
$0.36
AssemblyAI
universal-3-pro
$0.45
get started free

400 free hours.
No credit card required.

Start transcribing in under 5 minutes. Full docs included.

Get API Key Free →Explore the Docs

No commitment. No sales call. Scales to hundreds of hours.