API Market
Google
ElevenLabsBest price
ElevenLabs Scribe API
Transcription with speaker labels
Accurate speech to text across 99 languages, with diarisation and word-level timestamps.
Speech to textDiarisationTimestamps99 languages
Quickstart
Authenticate with a bearer token from your dashboard, then POST the request below.
curl -X POST https://api.viddly.io/v1/audio/generations \
-H "Authorization: Bearer $VIDDLY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs-scribe",
"audio_url": "<your audio_url>",
"diarize": true
}'Parameters
| Name | Type | Default | Description |
|---|---|---|---|
| audio_url* | string | — | Audio or video file to transcribe. |
| diarize | boolean | true | Label each speaker separately. |
| language | string | — | ISO code. Omit to auto-detect. |
Similar models
SunoPopular
Suno
Suno v5
Text to Music
Full songs with vocals from a prompt
Try it$0.850 / track~60s
ElevenLabs
ElevenLabs
ElevenLabs v3
Text to SpeechVoice Cloning
Lifelike speech in 70+ languages
Try it$0.045 / 1K characters~2s
GoogleNew
Gemini 3 Flash TTS
Text to Speech
Expressive multi-speaker narration
Try it$0.020 / 1K characters~2s