Transcripts
Who said what, after the call
Each participant's microphone is transcribed on its own, so every line has a speaker. Turn it on for a project, or request it for one session after the call ends.
Transcripts
One line, one speaker
Speech-to-text runs on each participant's microphone separately. The speaker on a line is that person's user id, the one you set on their connection token.
On for a project, or one session
Turn it on in the dashboard, or with
PUT /v1/projects/:id/transcription(enabledandlanguage). Or request one session that has ended withPOST /v1/sessions/:id/transcript. Asking again returns the transcript already queued, running or finished.Per speaker, or one language
autodetects each speaker's language.multiis for someone who switches languages mid-sentence. A BCP-47 tag such asenorpt-BRtranscribes everyone in that language.JSON, subtitles, or captions
GET /v1/sessions/:id/transcriptreturns the cues. Add?format=vtt,srtortxt, and?lang=for one language. Replay in@synento/playershows the same cues as captions.API, SDK, CLI and MCP
Node:
requestTranscript(). CLI:synento transcript --request. MCP:request_transcriptandget_transcript. Subscribe totranscript.readyinstead of polling.Billed on speech, not silence
Silence and muted stretches are removed before anything is sent, and only that speech is billed, summed over participants. Both plans include 60 minutes a month. Past that, Free stops and pay-as-you-go is $0.006 per transcribed minute.
Deleted with the session
Audio is sent to Deepgram only for a transcript you turned on or asked for, with model training opted out. The transcript is stored with the recording, deleted with the session, and redacting a participant removes their lines.
# Turn transcripts on for every session in a project.
curl -X PUT https://api.synento.com/v1/projects/$PROJECT_ID/transcription \
-H "Authorization: Bearer $SYNENTO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"enabled": true, "language": "auto"}'
# Or request one session after it has ended. Asking again is safe.
curl -X POST https://api.synento.com/v1/sessions/$SESSION_ID/transcript \
-H "Authorization: Bearer $SYNENTO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"language": "auto"}'
# Read it. format is vtt, srt or txt. lang keeps one language.
curl -s "https://api.synento.com/v1/sessions/$SESSION_ID/transcript?format=vtt" \
-H "Authorization: Bearer $SYNENTO_API_KEY"Keep exploring
Record the calls your product runs on.
Sign up for a free account. Replay, MP4 export and post-call transcripts are included, and a coding agent can set the integration up from llms.txt.