integrations.yml,
then name that group on the channel’s asr or tts, or as voice.asr and
voice.tts in agent.yml. Recognition and
synthesis are chosen separately, so you can mix providers. To use a provider
that is not built in, see Custom speech providers.
Choose a provider
Setprovider on the model group, and choose models and voices per language in
language_map. Point the channel, or
agent.yml, at the group’s id:
integrations.yml
Set the API key in your environment or
.env. If a key is missing, Mantle logs
the missing variable and the voice conversation can’t start. In the Inspector, you
see a “Voice isn’t set up yet” warning.
Configure Speechmatics Agent STT as its own model group:
integrations.yml
language_map:
integrations.yml
GRADIUM_API_KEY for both providers. Its default synthesis voice
is YTpq7expH9539ERJ; set a different voice for each language as needed.
Defaults
If the Inspector omits a side, andvoice.asr or voice.tts does not set it
either, that side still works with only DEEPGRAM_API_KEY, using Deepgram’s
earlier models:
Those defaults are English, even if
agent.language is another language. For
another language, set language_map
on the model group. Telephony channels have no defaults, so set both sides on
the channel or in agent.yml.
Speech recognition settings
Settings other thanprovider, api_key, and language_map go on the ASR
model, next to provider.
Speech synthesis settings
Settings other thanprovider, api_key, and language_map go on the TTS
model, next to provider.
For example, select an Inworld voice and language in
language_map:
integrations.yml
language_map:
integrations.yml
timeout (seconds, default 30).
Synthesized replies are cached in memory, so a repeated line, such as a
greeting, plays without a new provider request.
Regional endpoints
To keep audio in a region, use the provider’s regional endpoint. For Deepgram, use a full WebSocket URL for both speech recognition and speech synthesis. Include the API path for the selected engine. Existing ASR configs with a host-only endpoint continue to work, but use a full URL for new configs:integrations.yml
integrations.yml, set
DEEPGRAM_BASE_URL, for example wss://api.eu.deepgram.com. Rasa adds the API
path for each engine. An endpoint in integrations.yml still wins.
For Speechmatics, region selects the Agent STT endpoint. The default global
endpoint routes to the nearest region; set eu, us, or au to pin a region.
Troubleshoot setup
Keep keys out of
integrations.yml, shared logs, and source control. When
switching providers, keep the other groups in model_groups. Speech settings
belong on the speech model group. The channel, or voice.asr and voice.tts
in agent.yml, names that group. Both are read from the live project; restart
to pick them up. Changing skills, or which group orchestrator.model_group
names, needs rasa train. See
integrations.yml for configuration lifecycles.
Use Test and monitor voice to distinguish recognition, turn
handling, tool, and playback failures before tuning a provider.
See also
integrations.yml→ Voice channels: model group ids,language_map,interruptions, andsilence_timeoutagent.yml→asrandtts: the project-wide speech group ids- Custom speech providers: use a provider that is not built in
- Rasa Community voice tuning walkthrough: a worked Deepgram Flux example with spoken formatting and recognition recovery; check its tested version before reusing its settings