Cohere Speech and audio

Capability boundary

The Cohere Speech and audio catalog describes the jobs this class of model is intended to solve. It does not mean that every listed model shares request fields, input limits, or output formats. Read each model card together with its lifecycle status, origin, and official source. A platform provider may host models from several original vendors, so both the displayed ID and origin matter.

Selection criteria

Speech and audio includes recognition, synthesis, realtime conversation, and general audio understanding, which cannot be reduced to one quality score. For recognition, measure word error rate, timestamps, speaker separation, language, and accents. For synthesis, compare naturalness, voice control, first-audio latency, and streaming playback. Realtime sessions also require interruption handling, echo and noise tests, conversation state, and tool use. Codec, sample rate, channels, and chunk boundaries must match the endpoint contract.

Integration and protocol boundary

Confirm the exact model ID, authentication method, endpoint, and request schema in the Cohere official documentation, then look for the same exact ID and supported endpoint in this site's model marketplace. Changing only the base URL does not guarantee an identical response contract. Streaming events, asynchronous jobs, file uploads, tool calls, and error payloads may require separate adapters.

Production checklist

Build a repeatable evaluation from representative inputs and record the model ID, parameters, input version, and result. Measure success rate, tail latency, throttling, timeout behavior, cost per completed task, and safety outcomes. Prepare a replacement path for preview or legacy models. The official catalog explains product boundaries; callable availability, channel status, and current pricing remain the responsibility of the model marketplace.