cinara

Appearance

API Keys ​

API keys let you use Cinara from your own apps and scripts. Everything a key makes is billed to your workspace's credits and listed in History.

Create a key ​

  1. Open API Keys in the sidebar, under Workspace.
  2. Type a Key name, for example "Course videos".
  3. Choose Create key.
  4. You see Your new key "name". Choose Copy and keep it somewhere safe, such as your app's environment settings.
  5. Choose Done.

You won't be able to see the key again. If you lose it, revoke it and create a new one.

Only workspace owners and admins can create or revoke keys. Others see "Only workspace owners and admins can create or revoke keys."

Manage keys ​

Under Keys you see how many keys you have, out of 20. Each key shows:

  • its name and the start of the key, for example cin_ab12…
  • when it was created, and when it was last used (or "never used")
  • Last 30 days and All time: generations and credits
  • a History link

Choose Revoke to stop a key. Cinara asks you to confirm: apps using it stop working straight away.

Keys can't be used to create or revoke keys. Sign in to Cinara to do that.

Use the API ​

  • Address: https://api.cinara.ai
  • Authentication: send your key in an xi-api-key header, or as Authorization: Bearer cin_….
  • The endpoints below accept widely used request formats, so existing speech scripts only need this address and your key.
  • Errors are JSON with error, message and detail. Failed work is refunded.

Text to speech ​

POST /v1/text-to-speech/{voice_id}

  • JSON body: text, optional model_id and voice_settings.speed.
  • model_id: speech (1 credit per character) or speech-hd (2). Any other id, or none, uses HD.
  • Optional output_format in the address: mp3_44100_128 or a lower MP3 rate.
  • Returns MP3.
bash
curl -X POST "https://api.cinara.ai/v1/text-to-speech/mentor?output_format=mp3_44100_128" \
  -H "xi-api-key: $CINARA_API_KEY" -H "Content-Type: application/json" \
  -d '{"text": "Hello from Cinara.", "model_id": "speech"}' --output hello.mp3

Forced alignment ​

POST /v1/forced-alignment

  • Multipart file (MP3, WAV, M4A, AAC, OGG, FLAC or WebM, up to 50 MB) and its text.
  • Returns characters and words with start and end times, which spell the text exactly, plus loss.
bash
curl -X POST "https://api.cinara.ai/v1/forced-alignment" \
  -H "xi-api-key: $CINARA_API_KEY" \
  -F file=@hello.mp3 -F text="Hello from Cinara."

Speech to text ​

POST /v1/speech-to-text

  • Multipart file, optional language_code, diarize and tag_audio_events.
  • Returns text, language_code and words (words, spacing and sound events with times and speaker_id).
  • The result also opens in Transcribe.
bash
curl -X POST "https://api.cinara.ai/v1/speech-to-text" \
  -H "xi-api-key: $CINARA_API_KEY" \
  -F file=@interview.mp3 -F diarize=true -F language_code=en

Sound effects ​

POST /v1/sound-generation

  • JSON text (up to 450 characters), optional duration_seconds (0.5 to 22; automatic when left out), prompt_influence (0 to 1) and loop.
  • Returns MP3.
bash
curl -X POST "https://api.cinara.ai/v1/sound-generation" \
  -H "xi-api-key: $CINARA_API_KEY" -H "Content-Type: application/json" \
  -d '{"text": "Footsteps on gravel, slow and steady", "duration_seconds": 5}' --output steps.mp3

Voices ​

  • Use Cinara voice ids such as mentor (Mentor · Nathan, a patient teacher) or haven (Haven · Claire, calm and reassuring).
  • Or use your own voices from Voice Library.
  • GET https://api.cinara.ai/v1/speech/options lists every voice with its character and names.

The API reference documents every endpoint, including music, images, video, dubbing, audiobooks and Drive. To use Cinara from Claude, ChatGPT, VS Code or Cursor, see Integrations.

Limits ​

  • Up to 20 active keys per workspace.
  • Key names up to 60 characters.
  • Each key can make up to 120 requests a minute. Past that, requests get 429 with Retry-After, and the message "Too many requests with this API key (up to 120 a minute). Wait a minute and try again."
  • Forced alignment files up to 50 MB.

Credits ​

  • API requests cost the same credits as the site, from the same balance.
  • Text to speech: 1 credit per character with speech, 2 with speech-hd. Without a Cinara model_id, HD is used (2 per character).
  • Speech to text and forced alignment: 100 credits per minute.
  • Sound effects: 20 credits per second of sound.
  • Every result is listed in History with the key's name and counted in the key's usage.
  • Failed work is refunded.

Tips ​

  • Create one key per app, so you can see its usage and revoke it alone.
  • Never put a key in a web page or a public repository. Keep it on your server.
  • Set model_id to speech when you don't need HD, to halve the cost.
  • Handle 429 responses by waiting for the Retry-After time.

Cinara · AI voice, music and video

© 2026 APBLD