Skip to content

[Feature]: Support for audio transcriptions in mistral provider #987

@TejasGhatte

Description

@TejasGhatte

Prerequisites

  • I have searched existing issues and discussions to avoid duplicates

Problem to solve

This will add support for transcriptions in mistral through bifrost along with openai, gemini and elevenlabs.

Proposed solution

Implement transcription method in mistral provider
Doc: https://docs.mistral.ai/capabilities/audio_transcription

  1. Add structs in core/providers/mistral/types.go
  2. Write convertors for transcription in core/providers/mistral/transcription.go
  3. Use the convertors in core/providers/mistral/mistral.go
  4. Update documentation in docs/features/unified-interface.mdx#provider-support-matrix

Existing Implementations:

  1. OpenAI: https://github.com/maximhq/bifrost/tree/main/core/providers/openai
  2. Gemini: https://github.com/maximhq/bifrost/tree/main/core/providers/gemini
  3. ElevenLabs: https://github.com/maximhq/bifrost/tree/main/core/providers/elevenlabs

Alternatives considered

No response

Area(s)

Core (Go)

Additional context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    Status

    Done

    Milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions