Create a voice and generate speech

1. 1

   Sign in to the Dashboard

   Open the login page and sign in. If you were invited by a teammate, use the account attached to that invitation.
2. 2

   Switch to the right product

   In the top-left corner of the Dashboard, select the Narya.ai product switcher and choose Text to Speech. The sidebar changes to that product’s pages.
3. 3

   Open Voices

   Select Voices in the sidebar, or go directly to /operator/voices.

The list shows every usable voice with its status, provider routes, recording and transcript counts, and the voice id once one exists. Built-in voices show Built-in in the Updated column and are ready without any setup.

1. 1

   Open the Create voice dialog

   The Create voice button is at the top right of the Voices page. The dialog offers three tabs: Upload, Record, and Import existing.
2. 2

   Upload or record the speaker

   Upload accepts clean audio or video of one speaker — no music, no background voices. Record shows a ~10-second script in 中文, 日本語, or English, and saves that script as the transcript automatically.
3. 3

   Name the voice and verify the sample

   Enter a Name that identifies the speaker and purpose. For uploads, the Verify the sample block appears: listen once, select the spoken language, and type the exact words into the transcript field (placeholder “Exact words spoken”).
4. 4

   Confirm speaker permission

   Tick “I have the speaker's permission to use and clone this voice”. The Create button stays disabled until you do.
5. 5

   Select Create voice

   With a complete transcript, the app opens the new voice and immediately shows the Add voice route dialog. If any transcript is still missing, finish it on the voice’s Samples tab first.
6. 6

   Choose providers

   Tick the providers that should host this voice: ElevenLabs, Fish Audio, or waffle 1.0 beta. Each uses its recommended model automatically, and the sparkle icon shows whether that route supports emotion tags. Select Add routes.
7. 7

   Watch route progress

   The Provider route progress card updates as each provider finishes independently. The canonical voice id appears as soon as the first clone is submitted; wait for at least one route to show Ready before using it.
8. 8

   Test before relying on it

   Select Test in playground in the voice header, generate representative text, and listen before assigning the voice to an Agent or an API integration.

When you upload several files at once, the dialog warns: “This transcript is saved to the first recording. Add the remaining transcripts on the voice page before cloning.” Open the voice’s Samples tab — the counter (for example 3/4 transcripts) shows what is missing, and each recording row has an Edit button for its language and transcript.

You can select Add recordings on the voice page at any time. New samples reach the providers on the next clone, so existing routes show Update available until you re-clone them (see below).

1. 1

   Open Create voice → Import existing

   The third tab of the Create voice dialog.
2. 2

   Choose the provider account and catalog

   Pick ElevenLabs or Fish Audio, then My voices (voices in the connected account) or Public voice library.
3. 3

   Search and preview

   Type a name and select Search. Each result offers an inline audio preview; selecting one fills the Name field.
4. 4

   Choose the Route model and import

   Pick the provider model for the route, confirm the permission checkbox, and select Import voice. The voice is usable right away — no samples, no cloning.

1. 1

   Open the voice → Test in playground

   The button in the voice header carries the voice into the Playground. You can also open the Playground directly and pick any ready voice in Settings → Voice.
2. 2

   Use representative text

   Test names, numbers, abbreviations, domain vocabulary, mixed-language phrases, punctuation, questions, and the emotional range your product needs.
3. 3

   Add emotion tags where supported

   On tag-capable routes, type [ to search tags inline, or use Auto Tag to let the editor suggest them. Unsupported routes show a warning and skip the tags.
4. 4

   Tune output settings

   Under Settings, choose the Output format (PCM, MP3, AAC, Opus, or μ-law) and an optional Speed override, then select Generate speech.
5. 5

   Review History

   Successful generations are saved to the voice’s History → Generations tab with provider, model, tags, format, and playable audio.

1. 1

   Open Integrations in the Dashboard

   Sign in at /login, then select Integrations in the sidebar (under the Config group), or go directly to /operator/keys. The page is titled API keys. Only workspace Owners and Admins see it — other roles get “API key management requires an organization Owner or Admin.”
2. 2

   Name and create the key

   Enter a descriptive Label such as checkout-voice-prod and select Create key.
3. 3

   Copy the key immediately

   A banner shows the full key exactly once: “Key created. Copy it now, it won’t be shown again.” The key starts with awp_. Only a hash is stored, so a lost key must be replaced, not recovered.
4. 4

   Store it server-side

   Put the key in your backend’s secret manager. Never ship it in browser or mobile code — browsers use short-lived tokens instead. The Issued keys table shows each key’s prefix, status, and last-used time, and a Revoke button that disables it immediately.

1. 1

   Get a voice id

   Copy it from the voice’s page in the Dashboard, or call GET /v1/voices with your key and pick an id from the response. Use a voice from the same environment as the key.
2. 2

   Send complete text

   POST /v1/tts with text, voice_id, and an output_format the voice supports. The response body is the audio bytes.

curl --request POST https://animated-waffle.narya.ai/v1/tts \
  --header 'Authorization: Bearer awp_your_key_here' \
  --header 'Content-Type: application/json' \
  --data '{
    "text": "Hello from Narya.",
    "voice_id": "<id from GET /v1/voices>",
    "output_format": "mp3_44100_128"
  }' \
  --output speech.mp3

1. 1

   Connect

   Open wss://…/v1/tts/stream with your workspace key as a bearer token. To keep the permanent key away from short-lived processes, your backend can instead call POST /v1/tts/stream-tokens and pass the returned 2-minute token.
2. 2

   Start a generation

   Send the start event with the voice, format, and request options documented in the event reference.
3. 3

   Append text in order

   Send text chunks as they become available. Signal with stop when no more text will arrive.
4. 4

   Play audio in order

   Decode each audio chunk using the delivered format. Do not reorder chunks, and handle terminal and error events explicitly.