Introducing Song Creator Pro — create music with AI, locally on your device. Try it now →
Voice Creator Pro logoVoice Creator Pro
Try For Free

Speech to Text API

Speech to text API with word timestamps and speaker labels

Send audio and get back the text with a start and end time for every word, labelled by speaker.

Available now as a local API in the desktop app. Cloud API coming soon.

Join the cloud API waitlistGet the desktop app
POST/api/v1/transcription/start
printf '{"audio_base64": "%s", "return_timestamps": true, "num_speakers": 2}' \
  "$(base64 < interview.wav | tr -d '\n')" > body.json
 
curl -X POST "http://127.0.0.1:8100/api/v1/transcription/start?sync=true" \
  -H "Content-Type: application/json" \
  -d @body.json

What developers build with it

It detects the language automatically, or you can set one. Ask for SRT instead of JSON when you need a subtitle file.

  • Searchable transcripts for podcast and interview archives
  • Meeting notes split by who said what
  • Timed text for editing tools that cut video by transcript
See the product page
Response
{
  "success": true,
  "text": "So how did the launch go? Better than we hoped.",
  "timestamps": [
    { "text": "So", "start_time": 0.0, "end_time": 0.21, "speaker": "SPEAKER_00" },
    { "text": "how", "start_time": 0.21, "end_time": 0.38, "speaker": "SPEAKER_00" },
    { "text": "Better", "start_time": 2.1, "end_time": 2.46, "speaker": "SPEAKER_01" }
  ]
}

Need transcription as a cloud API instead of running locally?

Join the cloud API waitlist

Endpoints

Speech to text endpoints

MethodPathWhat it does
POST/api/v1/transcription/startTranscribe audio, as JSON or SRT
GET/api/v1/transcription/progressPoll a transcription started without sync
POST/api/v1/transcription/cancelCancel a running transcription

Quickstart

Make your first request in three steps

Install the app, turn on the API and send your first request.

API reference

Full API reference

Every endpoint, with its parameters and responses.

Cloud API

Join the cloud API waitlist

We're building a cloud API. Pick the features you need and roughly how much you'd use, and your answers decide which ones come first.

Which features do you need?

We'll only email you about the API. Unsubscribe anytime.

FAQ

Common Questions

Yes. It attributes each part of the transcript to a speaker automatically. Set num_speakers when you know how many people are talking.

Per word. Set return_timestamps to true and each word comes back with its start and end time in seconds, plus a speaker label when speaker detection ran.

Yes. Call /api/v1/transcription/start with sync=true, output_format=srt and return_timestamps set to true, and the response is a SubRip subtitle file.

No. Through the desktop app's local API, transcription runs on your own computer and the audio never leaves it.

Explore

Related APIs

Text to speech

Turn text into speech with preset speakers in 10 languages.

Voice cloning

Clone a voice from a short clip and speak new text with it.

Voice design

Describe a voice in words and generate speech in it.

Dubbing

Dub videos into 21 languages, keeping each speaker's voice.

Subtitles

Generate SRT caption files with word-level timing.

Clips

Cut long videos into short, captioned clips.

AI Cut

Remove silences, filler words and bad takes, then render.

Avatars

Make a lip-synced talking-head video from one photo.

Voice changer

Re-voice a recording while keeping its timing and emotion.

Audiobooks

Narrate a manuscript with a voice for every character.