Phonic
Forty-two multilingual voices in more than 50 languages, with speed control, for Phonic TTS.
Phonic is a speech-to-speech company that also offers a text-to-speech API. Phonic tuning is passed in synthesizer.options.
You can also set these in the portal under Extra Options on the speech credential, in which case they apply to every request that uses that credential. Settings supplied on the verb take precedence.
Credential
Create an API key in your Phonic account. jambonz sends the key as Authorization: Bearer <api key>. Add it as a Phonic speech credential in the portal or API, using the vendor id phonic. Phonic is used for text-to-speech only.
The credential can also set a model and an API host; see Endpoint override.
Voices and languages
The only model is merritt, which Phonic uses when no model is set.
The portal asks Phonic for the voices your API key can use, including custom voices provisioned for your workspace, and lists every voice under every language, the voices that speak that language best first. If Phonic can’t be reached, it shows the 42 base voices (sabrina, grant, landon, virginia, eleanor, and others). Some voices have an accent, which Phonic lists in its voices page.
jambonz sends the language code from synthesizer.language without its region, for example de for de-DE; nb and nn are sent as no, and tl as fil. A language Phonic does not support is not sent, so Phonic speaks English instead of rejecting the request.
jambonz requests Phonic audio as 16-bit PCM at 24 kHz and resamples it to the call’s rate.
Options
Every option is optional. An option you don’t set is not sent, so Phonic’s own default applies.
Speaking rate, from 0.5 to 1.5. Phonic’s default is 1.2.
Model. Overrides the model on the credential. Only merritt is available.
API host. Overrides the API host on the credential; see Endpoint override.
Endpoint override
To use a different Phonic endpoint, set the API base URL on the credential, or api_uri in its Extra Options or in synthesizer.options. It is a host name such as api.phonic.ai; a trailing / is ignored, and an http:// scheme connects without TLS. Leave it out to use api.phonic.ai.
Streaming
Phonic has no token-streaming websocket for text-to-speech (its websocket is for speech-to-speech conversations), so it does not support TTS streaming: use it for one-shot say, not for say with stream: true or the agent verb.